© 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. 36675
    Prev
    Next
    INDEX
    Explanations

    terms related to moisture and substances that retain moisture

    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
    739
    +0.15
    0.8%
    496
    +0.13
    0.6%
    7
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.15
    0.17
    352
    +0.13
    0.14
    151
    +0.12
    0.18
    Negative Logits
     Shack
    -0.75
     Redemption
    -0.69
    mire
    -0.68
    VERTISEMENT
    -0.67
    robe
    -0.65
     Leap
    -0.63
    otomy
    -0.61
     Whale
    -0.60
    flat
    -0.60
    stable
    -0.59
    POSITIVE LOGITS
    aceous
    0.72
    ibrary
    0.66
    iage
    0.65
    ersive
    0.64
    aiman
    0.63
    atical
    0.63
    issance
    0.61
    inois
    0.61
    tarians
    0.61
    xtap
    0.60
    Activations Density 8.045%

    No Known Activations