© 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. 1760
    Prev
    Next
    INDEX
    Explanations

    locations and institutions, possibly related to politics or public figures

    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
    480
    +0.22
    1.1%
    640
    +0.19
    0.9%
    679
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.22
    0.08
    640
    +0.19
    0.07
    430
    +0.15
    0.07
    Negative Logits
     manif
    -0.73
     nuts
    -0.70
     masse
    -0.67
     enjoyment
    -0.64
     oxy
    -0.64
     parity
    -0.63
     prototyp
    -0.63
     inqu
    -0.63
     brut
    -0.63
     biological
    -0.63
    POSITIVE LOGITS
     Photograph
    1.22
     Photo
    1.08
     REUTERS
    1.03
    jpg
    1.02
     Caption
    1.02
     PHOTO
    1.01
     Photographer
    1.01
     Hide
    0.97
     Courtesy
    0.97
    Photo
    0.97
    Activations Density 0.225%

    No Known Activations