© 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. 7190
    Prev
    Next
    INDEX
    Explanations

    medical and scientific terms or phrases related to research and health

    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
    642
    +0.22
    0.7%
    288
    +0.20
    0.7%
    216
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    96
    +0.22
    0.04
    21
    +0.20
    0.03
    642
    +0.17
    0.02
    Negative Logits
    estern
    -1.01
    uge
    -0.98
    EEK
    -0.95
    INESS
    -0.95
     Braun
    -0.94
    UGE
    -0.93
     Lauder
    -0.92
     Doodle
    -0.92
    orse
    -0.91
    atron
    -0.89
    POSITIVE LOGITS
    ities
    1.15
    tenance
    1.11
     careg
    1.01
    ignment
    0.99
     distingu
    0.99
    itative
    0.99
    alysed
    0.98
     antagonist
    0.95
    ebted
    0.93
    boards
    0.91
    Activations Density 0.377%

    No Known Activations