© 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 EvalsExportsAPI 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. 17949
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical and political entities, especially those involving socialism and specific regions or conflicts

    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
    180
    +0.10
    0.5%
    541
    +0.10
    0.4%
    560
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.10
    0.06
    288
    +0.10
    0.06
    57
    +0.09
    0.03
    Negative Logits
    idious
    -0.82
    ful
    -0.71
    erella
    -0.70
    ueless
    -0.68
    urious
    -0.67
    risome
    -0.66
    uitous
    -0.65
    icular
    -0.65
    worldly
    -0.63
    arcity
    -0.63
    POSITIVE LOGITS
     Conference
    0.80
     Partnership
    0.79
     Intermediate
    0.78
    Assembly
    0.76
    ities
    0.76
    ties
    0.76
    scill
    0.74
    hood
    0.73
     Association
    0.73
    ITIES
    0.72
    Activations Density 0.191%

    No Known Activations