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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7275
    Prev
    Next
    INDEX
    Explanations

    information related to a variety of topics, including games, publications, technology, and literature

    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
    582
    +0.17
    0.6%
    540
    +0.16
    0.5%
    270
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    540
    +0.17
    0.08
    271
    +0.16
    0.05
    582
    +0.16
    0.05
    Negative Logits
    pora
    -1.11
     Beir
    -1.04
    ortium
    -1.03
     Apost
    -0.97
    gencies
    -0.95
    thening
    -0.94
    ascus
    -0.93
     Unic
    -0.92
    ixed
    -0.87
    fty
    -0.87
    POSITIVE LOGITS
    wright
    1.84
    ername
    1.75
    plays
    1.45
    testers
    1.44
    GROUND
    1.44
    testing
    1.44
    lists
    1.40
    test
    1.29
    dates
    1.27
    tested
    1.24
    Activations Density 1.162%

    No Known Activations