© 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 Local
    9. 6-RES_SCL-AJT
    11. 36232
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions, treatments, and cascade processes, possibly linked to the field of healthcare or scientific research

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    38
    +0.11
    0.6%
    578
    +0.10
    0.5%
    699
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    38
    +0.11
    0.11
    159
    +0.10
    0.08
    504
    +0.10
    0.07
    Negative Logits
    ãĥīãĥ©ãĤ´ãĥ³
    -0.74
    tenance
    -0.70
    itude
    -0.67
    itud
    -0.64
    mares
    -0.63
    ãĥĥãĤ¯
    -0.62
    itia
    -0.62
    aye
    -0.60
    thren
    -0.59
    acca
    -0.59
    POSITIVE LOGITS
    REG
    0.82
    SI
    0.77
    LER
    0.76
    BIT
    0.75
    ILE
    0.73
    ITION
    0.73
    UAL
    0.72
    IBLE
    0.72
    FAULT
    0.72
    ERG
    0.71
    Activations Density 8.491%

    No Known Activations