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

    Neuronpedia

    Jacobian LensNEW
    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. 17498
    Prev
    Next
    INDEX
    Explanations

    terms related to political ideologies and organizations, particularly socialist and unionist groups

    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
    447
    +0.13
    0.6%
    724
    +0.11
    0.5%
    458
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.09
    724
    +0.11
    0.09
    225
    +0.10
    0.07
    Negative Logits
    yss
    -0.74
    nen
    -0.69
     seams
    -0.66
    SN
    -0.63
    acterial
    -0.62
     swat
    -0.62
    pload
    -0.58
    7601
    -0.57
    lit
    -0.57
    zyme
    -0.57
    POSITIVE LOGITS
     underpin
    0.73
    houses
    0.73
    tones
    0.70
    heid
    0.69
    aeda
    0.69
    enance
    0.66
    âĢİ
    0.66
    SPONSORED
    0.66
    smanship
    0.65
    NESS
    0.65
    Activations Density 0.506%

    No Known Activations