© 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. 10349
    Prev
    Next
    INDEX
    Explanations

    neuroscience and academic institution names

    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
    283
    +0.15
    0.7%
    377
    +0.15
    0.7%
    370
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.15
    0.07
    343
    +0.15
    0.06
    288
    +0.12
    0.08
    Negative Logits
    apers
    -0.80
    ively
    -0.71
    efer
    -0.66
    ASON
    -0.65
    encers
    -0.64
    afort
    -0.64
    asons
    -0.62
    mons
    -0.61
    iple
    -0.61
     Nadu
    -0.61
    POSITIVE LOGITS
    keley
    0.95
    axter
    0.92
    wana
    0.90
    reath
    0.86
    ruary
    0.85
    oreal
    0.81
    amboo
    0.80
    ucket
    0.78
    EGIN
    0.78
    strap
    0.78
    Activations Density 0.446%

    No Known Activations