© 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. 35725
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to politics, medicine, and literature

    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
    375
    +0.07
    0.5%
    743
    +0.07
    0.4%
    316
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.07
    0.21
    288
    +0.07
    0.20
    709
    +0.06
    0.11
    Negative Logits
    pora
    -0.59
    axies
    -0.59
    perial
    -0.57
    ograph
    -0.56
    enei
    -0.56
    actic
    -0.56
    endment
    -0.55
    ocene
    -0.55
    ngth
    -0.54
    anguage
    -0.54
    POSITIVE LOGITS
     Bind
    0.64
     Ruin
    0.58
    IRO
    0.56
    ãĤ¡
    0.54
    lish
    0.53
     Walters
    0.53
     Schiff
    0.52
     Andrews
    0.50
     Johnston
    0.50
     Julie
    0.49
    Activations Density 7.280%

    No Known Activations