© 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. 7587
    Prev
    Next
    INDEX
    Explanations

    texts related to political events, such as debates and arrests, or accidents and emergencies, like shootings and malfunctions

    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
    481
    +0.13
    0.6%
    373
    +0.12
    0.5%
    452
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    181
    +0.13
    0.04
    48
    +0.12
    0.03
    284
    +0.10
    0.03
    Negative Logits
    llan
    -0.91
    Apps
    -0.82
    reads
    -0.80
    Works
    -0.79
    ISO
    -0.78
    iom
    -0.75
    Companies
    -0.74
    ml
    -0.72
    prints
    -0.71
    Sty
    -0.70
    POSITIVE LOGITS
     poisoning
    1.13
     disaster
    1.09
     blight
    1.01
     crime
    0.99
     catastrophe
    0.98
     abuse
    0.98
     persecution
    0.97
     menace
    0.97
     disturbance
    0.96
     depression
    0.96
    Activations Density 0.305%

    No Known Activations