© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 16666
    Prev
    Next
    INDEX
    Explanations

    actions involving physical violence or conflict

    oai_token-act-pair · gpt-3.5-turbo

    recurring punctuation patterns, specifically commas in contexts involving actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.81
    "}],"
    -0.76
    ctions
    -0.74
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.73
    hower
    -0.72
     <[
    -0.71
    obyl
    -0.71
    enance
    -0.71
     ãĤµ
    -0.69
    ln
    -0.69
    POSITIVE LOGITS
     injuring
    1.26
     wounding
    1.17
     authorities
    1.15
     according
    1.12
     prosecutors
    1.07
     causing
    1.06
     prompting
    1.05
     police
    1.00
     witnesses
    1.00
     stabbing
    0.98
    Activations Density 0.162%

    No Known Activations