© 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 24576
    9. 8-RES_FS24576-JB
    11. 22174
    Prev
    Next
    INDEX
    Explanations

    verbs and terms related to resolution and problem-solving

    oai_token-act-pair · gpt-4o-miniTriggered 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
    497
    +0.10
    0.4%
    195
    +0.10
    0.4%
    727
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    624
    +0.10
    0.02
    251
    +0.10
    0.02
    448
    +0.10
    0.02
    Negative Logits
    ylon
    -0.68
    adobe
    -0.68
    edom
    -0.66
    oho
    -0.64
    ingham
    -0.63
    aah
    -0.62
    aq
    -0.62
    onew
    -0.62
    haw
    -0.61
    é¾įå
    -0.60
    POSITIVE LOGITS
     solely
    0.97
     centered
    0.91
     primarily
    0.88
     loosely
    0.88
     principally
    0.87
     squarely
    0.87
     toward
    0.86
     mainly
    0.83
     revolving
    0.81
     chiefly
    0.80
    Activations Density 0.057%

    No Known Activations