© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11862
    Prev
    Next
    INDEX
    Explanations

    references to real-life events, particularly those that involve controversy or misinformation

    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
    116
    +0.11
    0.5%
    123
    +0.10
    0.5%
    387
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    298
    +0.11
    0.03
    387
    +0.10
    0.03
    451
    +0.10
    0.03
    Negative Logits
    soever
    -0.75
    é¾įå¥ij士
    -0.69
     belonged
    -0.66
    hawks
    -0.63
     moderates
    -0.61
     wisely
    -0.60
    enery
    -0.59
    occupied
    -0.59
     meanwhile
    -0.58
     Rossi
    -0.58
    POSITIVE LOGITS
     downfall
    0.97
     eventual
    0.88
    ãĥĩãĤ£
    0.85
     lasting
    0.81
     breakdown
    0.81
     conclusion
    0.81
     demise
    0.79
     deaths
    0.79
     paralysis
    0.79
     deterioration
    0.78
    Activations Density 0.302%

    No Known Activations