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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1674
    Prev
    Next
    INDEX
    Explanations

    names of notable historical figures

    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
    696
    +0.18
    0.6%
    504
    +0.15
    0.5%
    89
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.18
    0.09
    430
    +0.15
    0.11
    232
    +0.14
    0.07
    Negative Logits
    umbai
    -1.16
    ramid
    -1.12
    ipers
    -1.08
    ornia
    -1.07
    mble
    -1.07
    oted
    -1.05
    otor
    -1.04
    unal
    -0.99
    unct
    -0.97
    ocrine
    -0.95
    POSITIVE LOGITS
     Tud
    1.31
     Hath
    1.13
     Francis
    1.10
     Roberts
    1.09
     Jenkins
    1.09
     Farrell
    1.09
     Moore
    1.07
     Wan
    1.07
     Donn
    1.04
     Cornwall
    1.04
    Activations Density 1.554%

    No Known Activations