© 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. 24406
    Prev
    Next
    INDEX
    Explanations

    legislative actions concerning bills being passed and debated in Congress or Parliament

    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
    476
    +0.13
    0.6%
    350
    +0.12
    0.6%
    714
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    350
    +0.13
    0.05
    476
    +0.12
    0.04
    300
    +0.10
    0.05
    Negative Logits
     tales
    -0.66
     divers
    -0.65
    pecially
    -0.65
    zsche
    -0.65
    ãĤ¤ãĥĪ
    -0.65
    obar
    -0.64
    anty
    -0.64
     attest
    -0.64
    si
    -0.64
     logos
    -0.63
    POSITIVE LOGITS
    osponsors
    1.19
     Congress
    1.19
    Senate
    1.19
     congress
    1.18
     Senate
    1.16
     senate
    1.16
     legislative
    1.12
     legislatures
    1.11
     Legislature
    1.08
     legislature
    1.07
    Activations Density 0.295%

    No Known Activations