© 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. 7473
    Prev
    Next
    INDEX
    Explanations

    phrases related to political ideologies and technological advancements

    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
    625
    +0.11
    0.5%
    447
    +0.10
    0.4%
    740
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.11
    0.09
    225
    +0.10
    0.08
    724
    +0.10
    0.08
    Negative Logits
    atorium
    -0.79
    same
    -0.65
    iversary
    -0.63
    versely
    -0.63
    REDACTED
    -0.62
    oux
    -0.62
     fingerprint
    -0.61
    ificantly
    -0.59
    aeper
    -0.58
    liest
    -0.58
    POSITIVE LOGITS
    hips
    1.15
    paces
    1.13
    mith
    1.09
    manship
    1.06
     abound
    1.05
    uits
    1.05
    poons
    1.05
    hip
    1.00
    pace
    0.96
    hooting
    0.94
    Activations Density 0.500%

    No Known Activations