© 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. 18847
    Prev
    Next
    INDEX
    Explanations

    references to thrift shopping or secondhand stores

    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
    128
    +0.10
    0.5%
    27
    +0.10
    0.5%
    585
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.03
    326
    +0.10
    0.02
    701
    +0.09
    0.01
    Negative Logits
    thia
    -0.77
    lar
    -0.76
    tics
    -0.69
    sei
    -0.67
    STEM
    -0.66
    cled
    -0.65
    dayName
    -0.64
    ORED
    -0.64
    ATOR
    -0.62
     Hanson
    -0.61
    POSITIVE LOGITS
    ifty
    0.98
    letcher
    0.89
    ift
    0.88
    itude
    0.87
    ieth
    0.86
    imore
    0.83
    inho
    0.79
    initely
    0.79
    unction
    0.78
    withstanding
    0.75
    Activations Density 0.059%

    No Known Activations