© 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. 11954
    Prev
    Next
    INDEX
    Explanations

    information related to current events or news articles

    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
    +0.23
    1.1%
    445
    +0.11
    0.5%
    620
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    384
    +0.23
    0.06
    225
    +0.11
    0.05
    236
    +0.10
    0.05
    Negative Logits
    galitarian
    -0.72
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.71
    radius
    -0.71
     Toro
    -0.71
    ãĥĺãĥ©
    -0.70
     masculinity
    -0.70
    eland
    -0.69
    SIZE
    -0.68
    bourne
    -0.67
    limit
    -0.66
    POSITIVE LOGITS
     interviews
    1.35
     briefings
    1.19
     emails
    1.19
     transcripts
    1.18
     podcasts
    1.15
     publications
    1.15
     presentations
    1.13
     blogs
    1.12
     memos
    1.12
     speeches
    1.11
    Activations Density 0.362%

    No Known Activations