© 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. 8765
    Prev
    Next
    INDEX
    Explanations

    phrases related to certainty or emphasis in statements

    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
    481
    +0.15
    0.7%
    447
    +0.12
    0.5%
    195
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.15
    0.02
    106
    +0.12
    0.02
    751
    +0.10
    0.02
    Negative Logits
    akable
    -0.77
    igers
    -0.71
    oulder
    -0.71
    ription
    -0.70
    uit
    -0.69
    efer
    -0.69
    cart
    -0.68
    Appearances
    -0.67
    alez
    -0.67
    itionally
    -0.67
    POSITIVE LOGITS
     unaware
    0.86
     unrelated
    0.78
     forgot
    0.76
     forgetting
    0.76
     incapable
    0.75
     oblivious
    0.74
     swayed
    0.74
     influenced
    0.72
     unaffected
    0.71
     lacking
    0.68
    Activations Density 0.034%

    No Known Activations