© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 4936
    Prev
    Next
    INDEX
    Explanations

    data related to statistical analysis, demographics, and occupations

    oai_token-act-pair · gpt-3.5-turbo

    decimal or floating-point numbers that include a period (.) followed by numerical sequences

    oai_token-act-pair · gpt-3.5-turboTriggered by @danbraun
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    487
    +0.12
    0.5%
    469
    +0.11
    0.5%
    399
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    176
    +0.12
    0.08
    640
    +0.11
    0.20
    107
    +0.10
    0.04
    Negative Logits
     Flavoring
    -0.80
    hement
    -0.79
    uncture
    -0.73
    essee
    -0.73
    lished
    -0.73
    rolet
    -0.72
    anners
    -0.72
    soDeliveryDate
    -0.71
    $.
    -0.71
     Carbuncle
    -0.71
    POSITIVE LOGITS
    ±
    0.80
     POW
    0.77
     msec
    0.72
    aunt
    0.64
    mic
    0.63
    ++++++++++++++++
    0.60
     Tradable
    0.59
     Mouth
    0.59
     Own
    0.59
    mean
    0.59
    Activations Density 8.840%

    No Known Activations