© 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. 20605
    Prev
    Next
    INDEX
    Explanations

    phrases related to running organizations or campaigns

    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
    270
    +0.14
    0.7%
    627
    +0.09
    0.4%
    567
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    270
    +0.14
    0.03
    155
    +0.09
    0.03
    70
    +0.09
    0.03
    Negative Logits
    alam
    -0.65
    udes
    -0.63
    ayers
    -0.62
    Lenin
    -0.62
    repre
    -0.60
    Ë
    -0.60
    oother
    -0.60
    ortium
    -0.58
    hor
    -0.57
    ï¸ı
    -0.57
    POSITIVE LOGITS
    escape
    0.94
     af
    0.89
    agate
    0.83
    aways
    0.82
    gs
    0.76
    running
    0.75
    ways
    0.72
     rampant
    0.71
    andi
    0.71
    dy
    0.70
    Activations Density 0.041%

    No Known Activations