© 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. 34966
    Prev
    Next
    INDEX
    Explanations

    technical or medical terminology related to various fields such as biology, technology, and medicine

    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
    745
    +0.07
    0.5%
    295
    +0.06
    0.4%
    67
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    404
    +0.07
    0.09
    97
    +0.06
    0.05
    353
    +0.06
    0.07
    Negative Logits
    ĸļ
    -0.52
    é¾
    -0.49
    tsky
    -0.49
    hig
    -0.46
     warr
    -0.46
    DragonMagazine
    -0.46
    é¾įå
    -0.45
    sburg
    -0.45
     Colt
    -0.45
    ilater
    -0.45
    POSITIVE LOGITS
    otine
    0.57
    ulous
    0.57
    ulum
    0.54
    usp
    0.53
    illin
    0.53
    apped
    0.52
    oming
    0.52
    keye
    0.52
    ulate
    0.51
    otic
    0.51
    Activations Density 6.337%

    No Known Activations