© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 5843
    Prev
    Next
    INDEX
    Explanations

    phrases related to ownership or unique characteristics

    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
    442
    +0.13
    0.5%
    243
    +0.12
    0.4%
    408
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.13
    0.06
    534
    +0.12
    0.04
    372
    +0.12
    0.04
    Negative Logits
    anwhile
    -1.14
    itement
    -1.00
    lehem
    -0.99
     Appears
    -0.91
     Dates
    -0.91
    ammers
    -0.91
     Mub
    -0.90
     incent
    -0.89
    antle
    -0.88
     Antar
    -0.88
    POSITIVE LOGITS
     unique
    1.17
     customized
    1.14
     version
    1.10
     custom
    1.09
     distinct
    1.06
     separate
    1.03
     personal
    1.01
     distinctive
    0.99
     branded
    0.99
     quirky
    0.98
    Activations Density 0.637%

    No Known Activations