© 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. 19314
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of a "pipe dream"

    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
    361
    +0.11
    0.5%
    442
    +0.11
    0.5%
    326
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.11
    0.01
    40
    +0.11
    0.01
    289
    +0.10
    0.01
    Negative Logits
    enance
    -0.92
    nesota
    -0.76
    eanor
    -0.73
    ãħĭ
    -0.70
    ivals
    -0.70
    imates
    -0.70
    doms
    -0.70
    apego
    -0.70
    ean
    -0.70
    ERAL
    -0.69
    POSITIVE LOGITS
    pipe
    1.06
     pipe
    1.02
     cleaners
    1.01
     pipes
    0.97
     cleaner
    0.85
     piping
    0.84
     Pipe
    0.83
     conduit
    0.81
     condu
    0.77
    fit
    0.76
    Activations Density 0.013%

    No Known Activations