© 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. 13581
    Prev
    Next
    INDEX
    Explanations

    medical terms and procedures that are primarily related to harm or injury

    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
    326
    +0.16
    0.6%
    608
    +0.13
    0.5%
    29
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.16
    0.08
    632
    +0.13
    0.05
    29
    +0.12
    0.06
    Negative Logits
    uder
    -1.08
    idious
    -0.94
     comprom
    -0.93
    inki
    -0.91
    agog
    -0.91
    abee
    -0.87
    rely
    -0.87
    kef
    -0.86
    obbies
    -0.84
    ionic
    -0.84
    POSITIVE LOGITS
    ::::::::
    1.10
    ::::
    1.05
    ;;;;;;;;
    1.04
    Pa
    1.01
    ãĤ¼ãĤ¦ãĤ¹
    0.98
    ,,,,,,,,
    0.95
    soon
    0.94
     {\
    0.93
     Globe
    0.93
    ,,,,
    0.92
    Activations Density 1.267%

    No Known Activations