© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 1326
    Prev
    Next
    INDEX
    Explanations

    language related to criminal activities and justice

    oai_token-act-pair · gpt-3.5-turbo

    references to witnessing or experiencing incidents of hate, violence, and racism

    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
    ufact
    -1.00
    Medic
    -0.82
     Canal
    -0.82
     canal
    -0.79
     resusc
    -0.79
     Miracle
    -0.77
    natureconservancy
    -0.77
     saline
    -0.76
    rosc
    -0.76
    quant
    -0.76
    POSITIVE LOGITS
     hate
    1.85
     Hate
    1.84
     hateful
    1.73
    hate
    1.67
     bigotry
    1.59
     swast
    1.51
     hatred
    1.50
     racist
    1.46
     intolerance
    1.46
     homophobic
    1.45
    Activations Density 0.474%

    No Known Activations