© 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. 10455
    Prev
    Next
    INDEX
    Explanations

    organizational and business-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
    481
    +0.11
    0.5%
    629
    +0.10
    0.5%
    413
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.11
    0.07
    55
    +0.10
    0.07
    300
    +0.10
    0.07
    Negative Logits
    ecd
    -0.79
     underscores
    -0.73
     Soph
    -0.71
     contrasts
    -0.70
     understandable
    -0.69
     Definitions
    -0.69
     illustrates
    -0.66
     underscore
    -0.65
    inctions
    -0.64
    ECD
    -0.63
    POSITIVE LOGITS
     indeed
    0.96
     secretly
    0.88
     "âĢ¦
    0.79
     plans
    0.77
     banned
    0.74
     rumored
    0.74
     actually
    0.74
     leaked
    0.73
     planned
    0.71
     upcoming
    0.71
    Activations Density 0.845%

    No Known Activations