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. 4298
    Prev
    Next
    INDEX
    Explanations

    sections of code related to computer programming

    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
    570
    +0.09
    0.5%
    255
    +0.09
    0.5%
    162
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    570
    +0.09
    0.02
    738
    +0.09
    0.08
    176
    +0.09
    0.06
    Negative Logits
    terday
    -0.78
     Ago
    -0.71
    arak
    -0.54
    ropolitan
    -0.54
    ccording
    -0.53
    regor
    -0.53
    aucuses
    -0.53
    20439
    -0.52
     sidx
    -0.51
    yright
    -0.51
    POSITIVE LOGITS
    '."
    0.60
    .'"
    0.55
     FIRE
    0.54
     Flight
    0.52
     behalf
    0.50
    !'"
    0.50
    izont
    0.49
    byss
    0.49
     safely
    0.49
     discriminating
    0.48
    Activations Density 10.106%

    No Known Activations