© 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 Local
    9. 6-RES_SCL-AJT
    11. 13163
    Prev
    Next
    INDEX
    Explanations

    scientific and medical terms related to anatomy, physiology, and diseases

    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
    403
    +0.10
    0.5%
    389
    +0.10
    0.5%
    347
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    701
    +0.10
    0.08
    738
    +0.10
    0.07
    314
    +0.09
    -0.06
    Negative Logits
     Fool
    -0.79
     Honor
    -0.74
     Grounds
    -0.73
     Benny
    -0.72
     Mansion
    -0.69
     Honour
    -0.69
     Yard
    -0.69
     Ll
    -0.67
     Manor
    -0.67
    =-=-
    -0.66
    POSITIVE LOGITS
    ological
    1.02
    ochemical
    1.00
    cular
    1.00
    ocyte
    0.99
    ogenic
    0.96
    ogen
    0.94
    ogenesis
    0.93
    zyme
    0.93
    ocytes
    0.92
    ologically
    0.92
    Activations Density 9.058%

    No Known Activations