Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 9928
    Prev
    Next
    INDEX
    Explanations

    specific mentions of names of people or organizations in news articles

    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
    662
    +0.12
    0.5%
    373
    +0.10
    0.5%
    416
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    662
    +0.12
    0.05
    416
    +0.10
    0.04
    223
    +0.09
    0.04
    Negative Logits
    plete
    -0.79
    ugu
    -0.79
    renheit
    -0.79
    lo
    -0.78
    uable
    -0.78
    nect
    -0.78
    ushima
    -0.75
    osph
    -0.73
    volt
    -0.73
    Interstitial
    -0.72
    POSITIVE LOGITS
     sides
    1.47
     sexes
    1.39
     halves
    1.25
     parties
    1.22
     genders
    1.13
     thirds
    0.89
     sets
    0.87
     factions
    0.84
     ends
    0.84
     camps
    0.82
    Activations Density 0.102%

    No Known Activations