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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 4231
    Prev
    Next
    INDEX
    Explanations

    details related to land management and animal populations

    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
    447
    +0.35
    1.7%
    393
    +0.16
    0.8%
    314
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    22
    +0.35
    0.19
    29
    +0.16
    0.18
    123
    +0.14
    0.14
    Negative Logits
    NOW
    -0.70
     alloc
    -0.60
     incumb
    -0.60
     convol
    -0.59
     ende
    -0.57
     incumbent
    -0.57
    Residents
    -0.55
     notwithstanding
    -0.53
     newcomers
    -0.53
     inconsist
    -0.53
    POSITIVE LOGITS
    ordinate
    1.03
    animate
    1.02
    ching
    1.01
    offensive
    0.97
    operative
    0.97
    bred
    0.95
    escap
    0.93
    humane
    0.92
    visible
    0.91
    effect
    0.91
    Activations Density 12.228%

    No Known Activations