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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1651
    Prev
    Next
    INDEX
    Explanations

    political statements and positions related to election campaigns and government decisions

    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
    725
    +0.11
    0.5%
    481
    +0.10
    0.4%
    242
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    725
    +0.11
    0.05
    242
    +0.10
    0.04
    680
    +0.10
    0.03
    Negative Logits
     Mages
    -0.77
     LTD
    -0.76
     NAD
    -0.74
    Sensor
    -0.73
    ibli
    -0.73
     mould
    -0.72
    uild
    -0.72
    AGES
    -0.70
     Guild
    -0.69
     ILCS
    -0.68
    POSITIVE LOGITS
     speeches
    1.16
     tweeting
    0.99
     tweets
    0.98
     aides
    0.98
    realDonaldTrump
    0.97
     rhetoric
    0.96
     bragging
    0.95
     remarks
    0.91
     surrog
    0.90
     keynote
    0.90
    Activations Density 0.677%

    No Known Activations