© 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. 4078
    Prev
    Next
    INDEX
    Explanations

    chronological data related to growth rates, projections, and market trends

    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
    +0.18
    0.8%
    173
    +0.13
    0.6%
    497
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    146
    +0.18
    0.09
    173
    +0.13
    0.08
    689
    +0.12
    0.09
    Negative Logits
    ishing
    -0.84
    isher
    -0.80
    oxin
    -0.78
    abilia
    -0.77
    ishes
    -0.74
    itionally
    -0.72
    warts
    -0.71
    flo
    -0.65
    izers
    -0.65
    izer
    -0.65
    POSITIVE LOGITS
    å¹
    0.90
     onwards
    0.78
    âĹ¼
    0.73
    assetsadobe
    0.67
    etheus
    0.66
    gaard
    0.65
     Brav
    0.64
     edition
    0.64
    peak
    0.63
    ãĤº
    0.62
    Activations Density 4.966%

    No Known Activations