© 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. 13716
    Prev
    Next
    INDEX
    Explanations

    information related to political news and legislative actions

    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
    464
    +0.14
    0.6%
    420
    +0.12
    0.6%
    513
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    464
    +0.14
    0.02
    252
    +0.12
    0.02
    456
    +0.10
    0.02
    Negative Logits
    ãģį
    -0.76
    é»Ĵ
    -0.72
     Republic
    -0.67
     nomine
    -0.62
     margins
    -0.61
    etheless
    -0.61
     Borderlands
    -0.61
    GBT
    -0.60
     foreground
    -0.60
     stemmed
    -0.59
    POSITIVE LOGITS
    ropolis
    1.35
    amorph
    1.31
    rics
    1.27
    adata
    1.24
    ropolitan
    1.23
    eor
    1.18
    allic
    1.13
    rix
    1.05
    abol
    1.03
    abolic
    1.00
    Activations Density 0.022%

    No Known Activations