© 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. 14364
    Prev
    Next
    INDEX
    Explanations

    mentions of the media in a negative 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
    288
    +0.13
    0.6%
    447
    +0.11
    0.5%
    644
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    336
    +0.13
    0.03
    509
    +0.11
    0.03
    132
    +0.09
    0.03
    Negative Logits
    ranged
    -0.71
    combe
    -0.70
    ta
    -0.70
     Pis
    -0.69
    İĭ
    -0.69
    ricular
    -0.66
    sql
    -0.66
    vasive
    -0.65
    0000000000000000
    -0.65
    etsk
    -0.65
    POSITIVE LOGITS
    eval
    1.45
     outlets
    1.25
     outlet
    1.06
     coverage
    1.02
     pundits
    0.95
     circus
    0.94
     mog
    0.90
     mogul
    0.90
     commentators
    0.88
     organisations
    0.87
    Activations Density 0.041%

    No Known Activations