© 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. 19969
    Prev
    Next
    INDEX
    Explanations

    terms related to political ideologies, particularly socialism and liberalism

    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
    481
    +0.21
    1.0%
    288
    +0.15
    0.7%
    447
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.21
    0.04
    724
    +0.15
    0.04
    481
    +0.14
    0.03
    Negative Logits
     Editors
    -0.65
     Recording
    -0.63
     CFR
    -0.59
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.58
    vol
    -0.57
     Representatives
    -0.56
    é£
    -0.56
    bah
    -0.56
    76561
    -0.56
    fman
    -0.56
    POSITIVE LOGITS
    ophobia
    0.87
    ophobic
    0.85
    anship
    0.84
    ophob
    0.82
    atism
    0.77
    ipedia
    0.76
     itself
    0.76
     perv
    0.76
     incarn
    0.75
     flourished
    0.73
    Activations Density 0.091%

    No Known Activations