© 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. 23778
    Prev
    Next
    INDEX
    Explanations

    references to illegal activities, particularly involving drugs, immigration, and trade

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with illegal activities and violations

    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
    efully
    -0.80
    oleon
    -0.74
     luckily
    -0.70
    akeru
    -0.69
    xual
    -0.68
    pb
    -0.68
    lov
    -0.67
    andals
    -0.66
    oried
    -0.66
    lik
    -0.64
    POSITIVE LOGITS
     immigrants
    1.08
     immigrant
    1.07
     aliens
    1.06
     immigration
    0.99
    ities
    0.97
     downloading
    0.96
     downloads
    0.95
     alien
    0.94
     substances
    0.93
     crossings
    0.90
    Activations Density 0.068%

    No Known Activations