© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 5545
    Prev
    Next
    INDEX
    Explanations

    years within sentences

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    146
    +0.15
    0.6%
    718
    +0.12
    0.4%
    246
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    146
    +0.15
    0.11
    598
    +0.12
    0.07
    689
    +0.11
    0.09
    Negative Logits
    heid
    -0.87
    ymes
    -0.86
    afort
    -0.84
     lawy
    -0.83
     ancest
    -0.81
    amins
    -0.79
    kef
    -0.76
    ancy
    -0.73
    akin
    -0.72
    naire
    -0.72
    POSITIVE LOGITS
    å¹
    1.07
    -'
    0.92
    ruary
    0.83
    yrinth
    0.81
     census
    0.78
     Cadillac
    0.76
     Aus
    0.76
     Coliseum
    0.75
     season
    0.74
     onwards
    0.74
    Activations Density 0.801%

    No Known Activations