© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10380
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning behaviors or actions in a narrative context

    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
    683
    +0.10
    0.5%
    576
    +0.10
    0.5%
    323
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.10
    -0.01
    232
    +0.10
    0.04
    406
    +0.10
    0.03
    Negative Logits
    Ļ½
    -0.69
    _-
    -0.69
    eon
    -0.66
    ouver
    -0.59
    nect
    -0.58
    ĪĴ
    -0.57
     tremend
    -0.57
     digestion
    -0.57
    hovah
    -0.57
     ensued
    -0.56
    POSITIVE LOGITS
    ongyang
    0.77
    glers
    0.70
    Roll
    0.69
    HP
    0.67
    Shift
    0.67
    ocene
    0.66
    ãĤī
    0.66
    Fax
    0.65
    aceous
    0.65
    hedral
    0.65
    Activations Density 0.120%

    No Known Activations