© 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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 13952
    Prev
    Next
    INDEX
    Explanations

    mentions of criminal activities and legal actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the article "a" in various contexts related to crime and weapons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     averages
    -0.77
    grounds
    -0.74
    stars
    -0.70
    runners
    -0.68
    imates
    -0.68
    én
    -0.68
    ateurs
    -0.67
    sheets
    -0.67
     Indust
    -0.67
     arcs
    -0.66
    POSITIVE LOGITS
    versive
    1.13
     bogus
    0.99
     fictitious
    0.99
     fake
    0.98
     prostitute
    0.98
    sexual
    0.95
     fraudulent
    0.94
     hoax
    0.92
     contraceptive
    0.92
     fetus
    0.91
    Activations Density 0.336%

    No Known Activations