© 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. 18204
    Prev
    Next
    INDEX
    Explanations

    phrases related to initiating discussion or causing reactions

    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
    195
    +0.12
    0.5%
    620
    +0.11
    0.5%
    646
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    646
    +0.12
    0.03
    201
    +0.11
    0.03
    195
    +0.11
    0.02
    Negative Logits
    esan
    -0.78
    é¾įå
    -0.72
    uters
    -0.70
    oped
    -0.70
    arant
    -0.69
    itte
    -0.66
     rendered
    -0.66
    çĦ
    -0.63
    ipped
    -0.62
     Passed
    -0.62
    POSITIVE LOGITS
     havoc
    1.18
     controversy
    1.11
     outrage
    0.98
     uproar
    0.94
     indignation
    0.92
     pandemonium
    0.92
     resentment
    0.91
     anger
    0.91
     anew
    0.90
     fires
    0.90
    Activations Density 0.069%

    No Known Activations