© 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. 1477
    Prev
    Next
    INDEX
    Explanations

    words related to political activities or positions

    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
    314
    +0.12
    0.6%
    373
    +0.12
    0.6%
    146
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.12
    0.01
    701
    +0.12
    0.03
    373
    +0.09
    -0.01
    Negative Logits
    esville
    -0.72
    jon
    -0.62
    rooms
    -0.62
    adem
    -0.61
    given
    -0.61
    bows
    -0.60
    accompanied
    -0.59
     lucky
    -0.58
    lore
    -0.57
    lift
    -0.57
    POSITIVE LOGITS
    ACA
    1.07
    AR
    1.07
    ETS
    1.03
    ALT
    1.02
    EN
    1.01
    OPS
    1.00
    CO
    1.00
    ELS
    0.99
    IK
    0.99
    KA
    0.99
    Activations Density 0.088%

    No Known Activations