© 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. 12935
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming-related terms

    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
    83
    +0.10
    0.4%
    255
    +0.10
    0.4%
    585
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    18
    +0.10
    0.09
    231
    +0.10
    0.07
    738
    +0.10
    0.06
    Negative Logits
    QB
    -0.72
    osate
    -0.71
    ingen
    -0.71
    assic
    -0.69
    tnc
    -0.69
    ury
    -0.68
    iants
    -0.68
    ssh
    -0.67
    plates
    -0.66
    urban
    -0.66
    POSITIVE LOGITS
     %%
    1.06
     instance
    0.81
     loop
    0.74
     Iter
    0.73
    instance
    0.72
     ];
    0.71
    ocument
    0.69
     [[
    0.68
     +=
    0.67
     Example
    0.67
    Activations Density 7.668%

    No Known Activations