© 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 12288
    9. 8-RES_FS12288-JB
    11. 10268
    Prev
    Next
    INDEX
    Explanations

    political terms related to extremism and controversial statements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    314
    +0.20
    0.9%
    472
    +0.14
    0.6%
    583
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.20
    0.01
    288
    +0.14
    0.07
    365
    +0.11
    0.03
    Negative Logits
     Lans
    -0.81
     captcha
    -0.75
     Landing
    -0.74
     deliveries
    -0.72
     HM
    -0.69
     delivery
    -0.69
     inhal
    -0.68
     Heard
    -0.68
     contacting
    -0.68
     payable
    -0.67
    POSITIVE LOGITS
    ism
    1.38
    ophobic
    1.38
    ophob
    1.32
    ivism
    1.32
    ophobia
    1.30
    femin
    1.30
    ocracy
    1.28
    acist
    1.27
    ivist
    1.25
    icism
    1.24
    Activations Density 0.414%

    No Known Activations