© 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. 17210
    Prev
    Next
    INDEX
    Explanations

    mentions of specific types of criminal activity, particularly related to assault and weapons

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of assault

    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
    FORE
    -0.71
    acca
    -0.67
     exch
    -0.65
     darn
    -0.64
    inki
    -0.64
    SOURCE
    -0.62
     snipp
    -0.61
     TIT
    -0.61
     Lumpur
    -0.60
     Tid
    -0.60
    POSITIVE LOGITS
    ive
    1.14
     rifles
    1.07
     rifle
    0.97
    iveness
    0.89
     Rifle
    0.86
     weapons
    0.84
    uous
    0.84
    ively
    0.83
     assault
    0.83
    orem
    0.80
    Activations Density 0.055%

    No Known Activations