© 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 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. 9011
    Prev
    Next
    INDEX
    Explanations

    sentences related to political and social issues

    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
    506
    +0.11
    0.5%
    496
    +0.11
    0.5%
    408
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    737
    +0.11
    0.03
    531
    +0.11
    0.03
    53
    +0.09
    0.03
    Negative Logits
    hement
    -0.70
    regon
    -0.64
    avery
    -0.64
    taboola
    -0.63
    utherland
    -0.62
    mbuds
    -0.61
    xes
    -0.61
    ipped
    -0.61
    ttes
    -0.60
    wright
    -0.60
    POSITIVE LOGITS
     happening
    0.85
    piring
    0.73
    natureconservancy
    0.67
     transpired
    0.66
     difference
    0.64
     happen
    0.64
     motivating
    0.62
     bothering
    0.62
     grunt
    0.62
     dstg
    0.61
    Activations Density 0.171%

    No Known Activations