© 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. 10988
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures and governmental actions

    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
    725
    +0.14
    0.6%
    430
    +0.13
    0.6%
    481
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.14
    0.08
    224
    +0.13
    0.07
    452
    +0.11
    0.05
    Negative Logits
    finder
    -0.80
     Craigslist
    -0.80
    uploads
    -0.78
    igslist
    -0.74
     miscarriage
    -0.71
    archive
    -0.69
    Reviewer
    -0.69
    icide
    -0.69
    usercontent
    -0.69
    quality
    -0.67
    POSITIVE LOGITS
     remarks
    1.23
     reiterated
    1.16
     emphas
    1.15
     praised
    1.10
     spoke
    1.08
     stressed
    1.06
     reiter
    1.05
     reiterate
    1.05
    Speaking
    1.01
     stressing
    1.00
    Activations Density 0.429%

    No Known Activations