© 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
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 33995
    Prev
    Next
    INDEX
    Explanations

    words related to programming and technical concepts

    oai_token-act-pair · gpt-3.5-turbo
    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
    59
    +0.14
    0.7%
    151
    +0.10
    0.5%
    192
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.14
    0.20
    288
    +0.10
    0.19
    151
    +0.10
    0.14
    Negative Logits
    enh
    -0.79
    endo
    -0.75
    elia
    -0.74
    orney
    -0.71
    agascar
    -0.66
    iary
    -0.63
    endi
    -0.62
    iaries
    -0.60
     Ridley
    -0.58
    ured
    -0.58
    POSITIVE LOGITS
    geant
    0.96
    vier
    0.90
    vers
    0.77
    vous
    0.77
    pent
    0.73
    pine
    0.70
    vised
    0.70
    gent
    0.69
    cot
    0.68
    fed
    0.68
    Activations Density 6.453%

    No Known Activations