© 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. 10026
    Prev
    Next
    INDEX
    Explanations

    negative or controversial comments or remarks made by public figures

    oai_token-act-pair · gpt-3.5-turbo

    disparaging remarks and comments related to controversial topics or individuals

    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
    utic
    -0.87
    ventions
    -0.82
    utical
    -0.79
    folio
    -0.76
     Pwr
    -0.76
    gency
    -0.75
    isd
    -0.74
    fax
    -0.73
    ETF
    -0.72
    enture
    -0.71
    POSITIVE LOGITS
     Mexicans
    1.44
     Latinos
    1.25
     Muslims
    1.22
     gays
    1.20
     Melania
    1.20
     homosexuals
    1.20
     Hispanics
    1.18
     Trayvon
    1.18
     immigrants
    1.18
     Adolf
    1.17
    Activations Density 0.457%

    No Known Activations