© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1478
    Prev
    Next
    INDEX
    Explanations

    phrases related to time and events

    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
    170
    +0.11
    0.5%
    274
    +0.10
    0.4%
    436
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.11
    0.06
    274
    +0.10
    0.04
    170
    +0.10
    0.04
    Negative Logits
     guiActiveUn
    -0.68
     violates
    -0.65
     inaccessible
    -0.65
    Fac
    -0.64
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.64
    pees
    -0.64
    inguishable
    -0.64
     licenses
    -0.63
    uggest
    -0.62
     trained
    -0.61
    POSITIVE LOGITS
    nings
    0.95
     outing
    0.91
     nonetheless
    0.75
     affair
    0.74
    night
    0.72
     opener
    0.71
    --------------------
    0.70
    ————
    0.70
     celebration
    0.69
    adan
    0.69
    Activations Density 0.330%

    No Known Activations