© 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 EvalsExportsinterp-engineNEWAPI 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. 22393
    Prev
    Next
    INDEX
    Explanations

    mentions of financial resources and support in various contexts

    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
    168
    +0.14
    0.6%
    218
    +0.12
    0.6%
    495
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    168
    +0.14
    0.04
    495
    +0.12
    0.04
    724
    +0.10
    0.04
    Negative Logits
    ipple
    -0.80
    EEP
    -0.69
    iasis
    -0.68
     Viol
    -0.68
    odge
    -0.66
     Topic
    -0.63
    Tip
    -0.63
    bons
    -0.63
    reet
    -0.63
    izen
    -0.63
    POSITIVE LOGITS
     manpower
    1.03
     sufficient
    1.02
     spare
    0.98
     adequate
    0.94
     resources
    0.93
    enough
    0.92
     sufficiently
    0.91
     capacity
    0.91
     enough
    0.89
     requisite
    0.89
    Activations Density 0.263%

    No Known Activations