© 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. 12524
    Prev
    Next
    INDEX
    Explanations

    phrases related to pressure or high stakes situations

    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
    102
    +0.12
    0.6%
    650
    +0.11
    0.5%
    4
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.12
    0.08
    55
    +0.11
    0.07
    650
    +0.10
    0.06
    Negative Logits
     Visit
    -0.76
    ycle
    -0.73
    edIn
    -0.68
    anto
    -0.68
     Contact
    -0.67
    azines
    -0.65
     Learns
    -0.64
     Common
    -0.63
    inances
    -0.62
     Particip
    -0.62
    POSITIVE LOGITS
     unmist
    1.03
     undeniable
    0.85
     muted
    0.85
     asymm
    0.82
     definitely
    0.81
     obvious
    0.81
     unclear
    0.81
     endless
    0.81
     palpable
    0.80
     legion
    0.79
    Activations Density 0.260%

    No Known Activations