© 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. 18824
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals holding prestigious positions

    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
    679
    +0.13
    0.6%
    224
    +0.12
    0.5%
    314
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    224
    +0.13
    0.05
    414
    +0.12
    0.03
    371
    +0.09
    0.04
    Negative Logits
    INGTON
    -0.73
    ensions
    -0.66
    ratom
    -0.65
    Sharp
    -0.63
    γ
    -0.62
    tro
    -0.61
    Cooldown
    -0.60
    Fine
    -0.59
    asso
    -0.59
    Medium
    -0.59
    POSITIVE LOGITS
    ially
    1.18
    ial
    0.97
    IAL
    0.96
    clinton
    0.95
     emer
    0.95
    boards
    0.90
    iors
    0.90
    person
    0.78
    dom
    0.77
    eki
    0.75
    Activations Density 0.050%

    No Known Activations