© 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. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 4063
    Prev
    Next
    INDEX
    Explanations

    financial and real estate-related terms and values

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    80
    +0.11
    0.5%
    90
    +0.11
    0.5%
    223
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    90
    +0.11
    0.04
    608
    +0.11
    0.05
    362
    +0.10
    0.04
    Negative Logits
    âĿ
    -0.64
    Ľ
    -0.61
    Newsletter
    -0.59
    REP
    -0.57
     (?,
    -0.56
    adian
    -0.54
    Definition
    -0.54
     ©
    -0.54
    ľ
    -0.54
    tif
    -0.53
    POSITIVE LOGITS
     whom
    0.96
     which
    0.87
    which
    0.85
    ardless
    0.77
    nown
    0.76
    _-
    0.72
     whose
    0.70
    cluding
    0.69
     whence
    0.68
    cause
    0.68
    Activations Density 0.220%

    No Known Activations