© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 34717
    Prev
    Next
    INDEX
    Explanations

    descriptions or discussions related to real or concrete things or concepts

    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
    +0.24
    1.1%
    132
    +0.11
    0.5%
    253
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.24
    0.28
    385
    +0.11
    0.26
    608
    +0.10
    0.28
    Negative Logits
    fu
    -0.71
    wich
    -0.70
     ashore
    -0.67
     Beware
    -0.65
     Carbuncle
    -0.64
    bay
    -0.63
    limit
    -0.63
    zy
    -0.62
     Caf
    -0.62
    oner
    -0.61
    POSITIVE LOGITS
    ity
    1.02
    izations
    1.01
    ITY
    1.00
    isation
    1.00
    idad
    0.97
    izable
    0.95
    ities
    0.89
    ignment
    0.86
    isations
    0.85
    ité
    0.83
    Activations Density 14.002%

    No Known Activations