© 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. 1511
    Prev
    Next
    INDEX
    Explanations

    references to old or outdated things within a context

    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
    735
    +0.10
    0.4%
    408
    +0.10
    0.4%
    21
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.10
    0.02
    161
    +0.10
    0.02
    507
    +0.09
    0.02
    Negative Logits
    utterstock
    -0.93
    ï¸ı
    -0.85
     ILCS
    -0.83
    ommod
    -0.82
    atography
    -0.80
    amera
    -0.80
    illation
    -0.79
    gur
    -0.78
    acca
    -0.73
    pard
    -0.73
    POSITIVE LOGITS
     fashioned
    1.41
     timers
    1.01
     standby
    0.97
    est
    0.93
    fashioned
    0.84
     stomp
    0.82
    school
    0.79
     school
    0.79
    bies
    0.78
     guard
    0.76
    Activations Density 0.023%

    No Known Activations