© 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. 18813
    Prev
    Next
    INDEX
    Explanations

    the word "Kushner" and related phrases

    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
    132
    +0.14
    0.6%
    346
    +0.13
    0.6%
    585
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    346
    +0.14
    0.01
    443
    +0.13
    0.01
    132
    +0.10
    0.01
    Negative Logits
     dividend
    -0.68
     pity
    -0.65
    falls
    -0.64
     advoc
    -0.63
    OWER
    -0.62
     membr
    -0.62
    ebin
    -0.62
     capit
    -0.61
    agents
    -0.61
    idine
    -0.60
    POSITIVE LOGITS
     Kushner
    1.28
     Goff
    0.99
    kefeller
    0.91
    kson
    0.82
     Rosen
    0.78
     Epstein
    0.78
    son
    0.78
    shaw
    0.76
    sson
    0.75
     Pad
    0.72
    Activations Density 0.018%

    No Known Activations