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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 34862
    Prev
    Next
    INDEX
    Explanations

    film-related terms and awards

    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
    314
    +0.09
    0.5%
    496
    +0.09
    0.5%
    267
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.09
    0.18
    76
    +0.09
    0.10
    81
    +0.08
    0.09
    Negative Logits
    etheless
    -0.64
    etsk
    -0.61
    lain
    -0.57
     heel
    -0.57
     bulk
    -0.56
     routine
    -0.55
     ç¥ŀ
    -0.53
     secular
    -0.53
     diesel
    -0.51
    anting
    -0.51
    POSITIVE LOGITS
     Expo
    0.85
     Festival
    0.78
     Awards
    0.77
     Guys
    0.77
    Works
    0.76
     Industry
    0.75
     Reviews
    0.73
     Critics
    0.73
     Geek
    0.71
     Machines
    0.70
    Activations Density 6.239%

    No Known Activations