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. 45568
    Prev
    Next
    INDEX
    Explanations

    instances where someone is attending an event or school

    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
    •Layer 6 UMAP region: Mixed in middle - local

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.31
    1.3%
    253
    +0.12
    0.5%
    445
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.31
    0.14
    385
    +0.12
    0.14
    124
    +0.11
    0.13
    Negative Logits
    cold
    -0.70
    slice
    -0.70
    worn
    -0.69
    theless
    -0.68
    deal
    -0.68
    arin
    -0.68
    irus
    -0.65
    tight
    -0.64
    sharp
    -0.61
    pmwiki
    -0.61
    POSITIVE LOGITS
     meetings
    0.87
     Attend
    0.87
     PAX
    0.83
     attend
    0.82
     conferences
    0.82
    eret
    0.82
     RTX
    0.82
    ees
    0.78
    URN
    0.77
     conventions
    0.77
    Activations Density 8.195%

    No Known Activations