Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 13523
    Prev
    Next
    INDEX
    Explanations

    information related to online forums and discussions

    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
    259
    +0.11
    0.5%
    720
    +0.10
    0.5%
    26
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.11
    0.08
    412
    +0.10
    0.07
    55
    +0.10
    0.07
    Negative Logits
    IDENT
    -0.68
     horizont
    -0.64
     behavi
    -0.64
    ITNESS
    -0.62
     creat
    -0.62
    hist
    -0.62
    ãĥ¼ãĥĨ
    -0.62
    negie
    -0.62
     traged
    -0.61
     nep
    -0.61
    POSITIVE LOGITS
    ################################
    0.89
     Edited
    0.86
    ########
    0.73
    ãħĭ
    0.72
     Posts
    0.72
     Bought
    0.69
    eals
    0.68
     âĨij
    0.68
    reply
    0.68
    region
    0.67
    Activations Density 3.499%

    No Known Activations