© 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. 36282
    Prev
    Next
    INDEX
    Explanations

    words related to cognitive disabilities and health conditions, specifically fetal alcohol syndrome

    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
    728
    +0.14
    0.7%
    57
    +0.11
    0.6%
    447
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    549
    +0.14
    0.09
    728
    +0.11
    0.06
    183
    +0.10
    0.10
    Negative Logits
     Colleges
    -0.65
     abiding
    -0.53
     Halls
    -0.53
    âĶģ
    -0.52
     Norn
    -0.52
     Skydragon
    -0.51
     indifferent
    -0.50
    é¾įå¥ij士
    -0.50
    craft
    -0.49
    HCR
    -0.49
    POSITIVE LOGITS
    xt
    0.86
    obar
    0.86
    itness
    0.83
    oms
    0.83
    ils
    0.82
    gey
    0.82
    isted
    0.80
    ortun
    0.79
    ogle
    0.78
    avour
    0.78
    Activations Density 8.478%

    No Known Activations