© 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 3072
    9. 8-RES_FS3072-JB
    11. 256
    Prev
    Next
    INDEX
    Explanations

    instances that emphasize urgency or a call to action

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    +0.11
    0.5%
    92
    +0.10
    0.5%
    514
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.11
    0.16
    514
    +0.10
    0.14
    352
    +0.10
    0.15
    Negative Logits
     Franch
    -0.85
     snail
    -0.75
     seiz
    -0.69
     obser
    -0.69
     disse
    -0.68
     antip
    -0.65
     dissemin
    -0.63
     mainland
    -0.61
     promul
    -0.61
     stomp
    -0.61
    POSITIVE LOGITS
    Ŀ
    1.74
    ¡
    1.43
    ¤
    1.20
    ¦
    1.19
    Ĵ
    1.17
    Ķ
    1.16
    ľ
    1.15
    ĺ
    1.13
    ª
    1.13
    ŀ
    1.13
    Activations Density 0.715%

    No Known Activations