© 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 12288
    9. 8-RES_FS12288-JB
    11. 9791
    Prev
    Next
    INDEX
    Explanations

    mentions of PlayStation consoles and related information

    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
    76
    +0.09
    0.4%
    628
    +0.09
    0.4%
    705
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    628
    +0.09
    0.02
    461
    +0.09
    0.02
    294
    +0.09
    0.01
    Negative Logits
    butt
    -0.87
     rh
    -0.68
    hart
    -0.68
     Alz
    -0.66
     Hamm
    -0.63
     Austrian
    -0.63
    glers
    -0.63
    nings
    -0.62
     Kazakh
    -0.62
     measles
    -0.62
    POSITIVE LOGITS
    FK
    1.02
    atile
    1.01
     Vita
    0.94
    LV
    0.87
    VR
    0.85
    RP
    0.81
    Ħ¢
    0.81
    ledge
    0.78
    GS
    0.77
     Store
    0.76
    Activations Density 0.030%

    No Known Activations