© 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. 26531
    Prev
    Next
    INDEX
    Explanations

    references to user interfaces and graphical user interfaces (UI/GUI)

    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
    211
    +0.11
    0.5%
    288
    +0.11
    0.5%
    479
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    211
    +0.11
    0.01
    435
    +0.11
    0.01
    326
    +0.10
    0.01
    Negative Logits
    iasis
    -0.77
    iary
    -0.74
    itude
    -0.73
    wagen
    -0.72
    nir
    -0.72
    nikov
    -0.67
     Volunte
    -0.66
    ieving
    -0.66
    milo
    -0.66
     Luthor
    -0.65
    POSITIVE LOGITS
    Kit
    1.08
    PDATE
    0.93
    BG
    0.91
    TAG
    0.90
    UI
    0.90
    ML
    0.87
    FW
    0.87
     Designer
    0.86
    HUD
    0.86
    UC
    0.81
    Activations Density 0.004%

    No Known Activations