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. 40244
    Prev
    Next
    INDEX
    Explanations

    directives or suggestions related to social media engagement

    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
    +0.21
    1.2%
    718
    +0.11
    0.6%
    393
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    718
    +0.21
    0.18
    608
    +0.11
    0.20
    393
    +0.07
    0.24
    Negative Logits
    é¾įåĸļ士
    -0.56
    erno
    -0.54
    ellation
    -0.53
    icipated
    -0.51
    ergus
    -0.50
    emort
    -0.50
    htaking
    -0.50
    soDeliveryDate
    -0.49
    alysed
    -0.49
    alf
    -0.48
    POSITIVE LOGITS
     remind
    0.78
     incorporate
    0.77
     adhere
    0.77
     endorse
    0.76
     indulge
    0.76
     acknowledge
    0.75
     mention
    0.73
     celebrate
    0.73
     emphasize
    0.72
     give
    0.72
    Activations Density 9.976%

    No Known Activations