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. 4234
    Prev
    Next
    INDEX
    Explanations

    short phrases about making trade-offs

    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
    481
    +0.12
    0.6%
    724
    +0.11
    0.5%
    447
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    724
    +0.12
    0.15
    485
    +0.11
    0.11
    225
    +0.10
    0.10
    Negative Logits
    ographs
    -0.81
    ograph
    -0.60
    writ
    -0.58
    roy
    -0.58
    lar
    -0.57
    head
    -0.56
     Tub
    -0.56
     Writ
    -0.55
    ãĥĺ
    -0.54
    gov
    -0.53
    POSITIVE LOGITS
    yip
    0.87
    olicy
    0.70
     complexity
    0.69
     tweak
    0.67
    ":""},{"
    0.67
     flexibility
    0.66
     compromise
    0.65
     adjustment
    0.64
     approach
    0.64
    rior
    0.63
    Activations Density 8.501%

    No Known Activations