© 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. 21951
    Prev
    Next
    INDEX
    Explanations

    terms related to extremism and political suppression

    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
    373
    +0.14
    0.6%
    83
    +0.10
    0.5%
    336
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.14
    0.01
    503
    +0.10
    0.01
    284
    +0.09
    0.01
    Negative Logits
     sadd
    -0.64
     arsenic
    -0.62
     steroids
    -0.61
     Ack
    -0.61
     Ao
    -0.60
     Typh
    -0.59
     dod
    -0.59
     Labrador
    -0.58
     Tec
    -0.58
     generous
    -0.57
    POSITIVE LOGITS
    antle
    1.26
    lins
    1.10
    acy
    1.06
    acists
    1.06
    phasis
    1.05
    acist
    1.03
    achine
    1.01
    nant
    0.99
    arkable
    0.96
    ilitary
    0.95
    Activations Density 0.017%

    No Known Activations