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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 13395
    Prev
    Next
    INDEX
    Explanations

    names of people and TV show titles

    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
    449
    +0.10
    0.5%
    752
    +0.10
    0.5%
    57
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    556
    +0.10
    0.11
    314
    +0.10
    -0.04
    634
    +0.10
    0.12
    Negative Logits
    caps
    -0.73
     Izan
    -0.70
     brim
    -0.69
    Materials
    -0.69
     Flavoring
    -0.66
    tip
    -0.66
    Shape
    -0.65
    wcsstore
    -0.64
    thirds
    -0.63
    Reviewed
    -0.62
    POSITIVE LOGITS
    .,
    0.84
    .?
    0.80
    .:
    0.78
    .;
    0.72
    .—
    0.71
    oire
    0.69
    ./
    0.68
    hyde
    0.66
    eteria
    0.66
     Sanctuary
    0.66
    Activations Density 8.367%

    No Known Activations