© 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. 40522
    Prev
    Next
    INDEX
    Explanations

    phrases related to written words, specifically focusing on words written in ink

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ink" used in various contexts

    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
    339
    +0.14
    0.7%
    289
    +0.13
    0.6%
    578
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.18
    326
    +0.13
    0.18
    346
    +0.11
    0.07
    Negative Logits
    nels
    -0.69
    cffffcc
    -0.68
    ADS
    -0.67
    rals
    -0.64
     hostages
    -0.63
    anchester
    -0.63
    PsyNetMessage
    -0.62
    ideos
    -0.61
     detrim
    -0.60
    ODE
    -0.60
    POSITIVE LOGITS
    jet
    1.05
     ink
    1.03
    manship
    0.97
    prints
    0.95
    lings
    0.91
     cartridges
    0.88
    sworth
    0.86
     Ink
    0.85
    atha
    0.81
    clip
    0.80
    Activations Density 5.967%

    No Known Activations