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. 45113
    Prev
    Next
    INDEX
    Explanations

    examples of processes or situations being carried out or functioning as intended

    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
    +0.14
    0.6%
    151
    +0.14
    0.6%
    307
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    138
    +0.14
    0.49
    447
    +0.14
    0.51
    64
    +0.12
    -0.15
    Negative Logits
    iens
    -0.83
    ists
    -0.76
    aily
    -0.74
    oleon
    -0.72
    ista
    -0.72
    ados
    -0.71
    isms
    -0.71
     arrivals
    -0.70
     favorites
    -0.68
    orem
    -0.67
    POSITIVE LOGITS
     communicated
    0.94
     positioned
    0.93
    ãĤ©
    0.92
     handled
    0.89
     behaved
    0.88
     awoken
    0.87
     dispose
    0.87
     challenged
    0.86
     accommod
    0.86
     understood
    0.85
    Activations Density 7.549%

    No Known Activations