© 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. 9834
    Prev
    Next
    INDEX
    Explanations

    names or surnames containing "ier."

    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
    238
    +0.13
    0.6%
    464
    +0.10
    0.5%
    497
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    464
    +0.13
    0.02
    659
    +0.10
    0.02
    326
    +0.09
    0.02
    Negative Logits
    ELS
    -0.67
    resh
    -0.66
    ORE
    -0.65
    Market
    -0.63
    TPS
    -0.63
    rew
    -0.61
    erest
    -0.61
    ajor
    -0.60
    ãĥĥãĥī
    -0.59
    ere
    -0.59
    POSITIVE LOGITS
    getic
    0.93
    ogly
    0.84
    cing
    0.84
    dain
    0.79
     dilig
    0.78
    cest
    0.78
    cer
    0.77
    cules
    0.76
    ced
    0.75
    hoe
    0.74
    Activations Density 0.102%

    No Known Activations