© 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. 18800
    Prev
    Next
    INDEX
    Explanations

    Filipino words related to government, such as titles, names, and locations

    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
    420
    +0.10
    0.5%
    265
    +0.10
    0.5%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    744
    +0.10
    0.03
    350
    +0.10
    0.03
    659
    +0.10
    0.03
    Negative Logits
    IAL
    -0.81
    AX
    -0.80
    ington
    -0.78
    ees
    -0.77
    APH
    -0.77
    FX
    -0.74
    atories
    -0.74
    ipal
    -0.73
    oids
    -0.73
    furt
    -0.73
    POSITIVE LOGITS
     lang
    0.87
     tha
    0.84
     bab
    0.78
     mah
    0.72
     opio
    0.69
     sar
    0.68
     bes
    0.68
     la
    0.66
     sher
    0.66
     buck
    0.65
    Activations Density 0.057%

    No Known Activations