© 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. 24526
    Prev
    Next
    INDEX
    Explanations

    terms related to receiving information from a news source

    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
    31
    +0.11
    0.5%
    617
    +0.10
    0.4%
    358
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    208
    +0.11
    0.02
    477
    +0.10
    0.02
    257
    +0.09
    0.02
    Negative Logits
     loophole
    -0.76
     mic
    -0.74
     IPM
    -0.68
    ecause
    -0.68
     param
    -0.66
     Nam
    -0.65
     Beir
    -0.62
     Mush
    -0.60
     hen
    -0.59
     Gamer
    -0.59
    POSITIVE LOGITS
    interstitial
    0.94
     Thumbnails
    0.76
    entimes
    0.73
    currency
    0.72
    ructose
    0.70
    push
    0.68
    åij
    0.67
    osion
    0.65
    artifacts
    0.65
    asts
    0.64
    Activations Density 0.035%

    No Known Activations