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. 40191
    Prev
    Next
    INDEX
    Explanations

    patterns in programming functions and code snippets

    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
    314
    +0.14
    0.5%
    525
    +0.13
    0.5%
    265
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.14
    -0.08
    314
    +0.13
    -0.01
    176
    +0.11
    0.03
    Negative Logits
     Lauder
    -0.92
     Jou
    -0.85
     condol
    -0.84
     forfe
    -0.80
     Falk
    -0.77
     Morg
    -0.77
     Kro
    -0.74
    Redd
    -0.74
     Adin
    -0.74
     Died
    -0.74
    POSITIVE LOGITS
     <!--
    0.84
    SEA
    0.77
     Sharks
    0.77
     CONTIN
    0.76
    acular
    0.76
    iami
    0.75
    anguages
    0.75
    imeters
    0.74
     Image
    0.73
    hello
    0.73
    Activations Density 2.694%

    No Known Activations