© 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. 36596
    Prev
    Next
    INDEX
    Explanations

    the phrase "never know."

    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
    617
    +0.10
    0.5%
    739
    +0.10
    0.5%
    152
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.10
    0.21
    213
    +0.10
    0.06
    228
    +0.10
    0.10
    Negative Logits
    phrine
    -0.66
    ciating
    -0.65
    endon
    -0.63
    ĪĴ
    -0.62
    inance
    -0.61
    adies
    -0.59
    otion
    -0.58
    ItemTracker
    -0.57
    inances
    -0.56
    ructose
    -0.56
    POSITIVE LOGITS
     how
    0.71
     whether
    0.69
     anymore
    0.68
     whats
    0.66
    how
    0.65
    ãĤ½
    0.61
    gat
    0.59
    rium
    0.58
     fri
    0.58
     ledge
    0.57
    Activations Density 8.321%

    No Known Activations