© 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. 1892
    Prev
    Next
    INDEX
    Explanations

    phrases related to political and societal issues

    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
    160
    +0.10
    0.4%
    290
    +0.09
    0.4%
    329
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    720
    +0.10
    0.06
    290
    +0.09
    0.05
    546
    +0.09
    0.05
    Negative Logits
     Moines
    -0.62
    ©¶æ
    -0.61
    iple
    -0.60
     mail
    -0.60
    orts
    -0.60
    iler
    -0.59
    ãĤ©
    -0.58
     commun
    -0.57
     NX
    -0.57
     mall
    -0.57
    POSITIVE LOGITS
    especially
    1.36
    particularly
    1.33
    something
    1.27
    including
    1.25
     namely
    1.14
    even
    1.10
    provided
    1.04
    until
    1.02
    which
    1.02
    thus
    1.00
    Activations Density 0.130%

    No Known Activations