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. 10036
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific Twitter handle, "@GlitterVelocity."

    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
    649
    +0.10
    0.5%
    525
    +0.10
    0.5%
    113
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.03
    284
    +0.10
    0.02
    288
    +0.09
    0.03
    Negative Logits
    fulness
    -0.80
    heit
    -0.79
     Simulator
    -0.76
    manship
    -0.72
    lied
    -0.71
    landish
    -0.70
    swer
    -0.69
    pour
    -0.68
    ritz
    -0.68
    retty
    -0.67
    POSITIVE LOGITS
    ocity
    1.28
    ikes
    0.74
    aries
    0.73
    ary
    0.71
    ogue
    0.71
    ORPG
    0.71
    istically
    0.70
     shif
    0.70
    Vel
    0.68
     Vaughn
    0.67
    Activations Density 0.109%

    No Known Activations