© 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 49152
    9. 8-RES_FS49152-JB
    11. 26565
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "home."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    501
    +0.11
    0.5%
    554
    +0.10
    0.5%
    372
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    372
    +0.11
    0.01
    201
    +0.10
    0.01
    501
    +0.10
    0.01
    Negative Logits
    sect
    -0.77
    alias
    -0.75
    roup
    -0.74
    conn
    -0.73
    erness
    -0.72
    etting
    -0.69
    thodox
    -0.69
    href
    -0.68
    azi
    -0.67
    Files
    -0.67
    POSITIVE LOGITS
     trophies
    0.82
     prizes
    0.74
     NX
    0.72
     podium
    0.70
     bragging
    0.68
     trophy
    0.67
     Ribbon
    0.67
     Wii
    0.67
     victory
    0.66
     $
    0.65
    Activations Density 0.009%

    No Known Activations