© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11896
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures and political events/actions

    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
    +0.18
    0.8%
    720
    +0.11
    0.5%
    492
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    492
    +0.18
    0.03
    91
    +0.11
    0.04
    558
    +0.10
    0.03
    Negative Logits
    omorph
    -0.76
     bins
    -0.75
    Stream
    -0.72
     detector
    -0.69
     detectors
    -0.67
     informants
    -0.67
     corners
    -0.66
    Maps
    -0.65
     catalog
    -0.65
     wells
    -0.65
    POSITIVE LOGITS
     appoint
    1.13
    elected
    1.10
     presided
    1.08
     appointed
    1.08
     appointing
    1.00
     democratically
    0.99
     inher
    0.92
    bernatorial
    0.92
     impeachment
    0.91
     hereditary
    0.90
    Activations Density 0.521%

    No Known Activations