© 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. 22495
    Prev
    Next
    INDEX
    Explanations

    phrases indicating significant financial influence or socio-political leverage

    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
    481
    +0.13
    0.6%
    389
    +0.11
    0.5%
    652
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    122
    +0.13
    0.04
    711
    +0.11
    0.02
    652
    +0.10
    0.04
    Negative Logits
    eatures
    -0.60
     Authors
    -0.58
    onement
    -0.58
    emonium
    -0.57
    orpor
    -0.57
    ecause
    -0.57
    Rah
    -0.56
    nesday
    -0.55
    Aren
    -0.55
     Relax
    -0.55
    POSITIVE LOGITS
     disabilities
    0.96
     penchant
    0.94
     knack
    0.94
     backgrounds
    0.93
     propensity
    0.88
     affinity
    0.87
     predis
    0.86
     flair
    0.86
     pedigree
    0.86
     allergies
    0.85
    Activations Density 0.320%

    No Known Activations