© 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. 6149
    Prev
    Next
    INDEX
    Explanations

    negative political and social terms related to extremist groups and ideologies

    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
    102
    +0.11
    0.5%
    631
    +0.11
    0.5%
    314
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    537
    +0.11
    0.02
    152
    +0.11
    0.02
    102
    +0.10
    0.02
    Negative Logits
    channelAvailability
    -0.73
     bearer
    -0.73
     ado
    -0.72
    anwhile
    -0.68
     disse
    -0.68
     Coverage
    -0.68
     Immunity
    -0.67
     diligence
    -0.65
     hereby
    -0.65
     coverage
    -0.65
    POSITIVE LOGITS
    Nazi
    1.21
    natal
    1.15
    traditional
    1.14
    liberal
    1.13
    colonial
    1.13
    fascist
    1.10
    Nazis
    1.06
    Georg
    1.04
    Soviet
    1.03
    classic
    1.00
    Activations Density 0.022%

    No Known Activations