© 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. 11-RES-JB
    11. 1450
    Prev
    Next
    INDEX
    Explanations

    mentions of unfortunate events or incidents

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating causes of events, particularly related to unfortunate circumstances

    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
     ÂŃ
    -0.61
    glers
    -0.52
     Quick
    -0.50
    Quick
    -0.50
    Next
    -0.49
    â
    -0.48
    RELATED
    -0.47
    buck
    -0.47
    Thankfully
    -0.45
    ½
    -0.45
    POSITIVE LOGITS
     homosexual
    0.81
    REDACTED
    0.73
     retarded
    0.73
     negro
    0.72
     plagiar
    0.69
     Plaintiff
    0.68
     slander
    0.67
     transsexual
    0.66
     âĸĪ
    0.66
     fraudulent
    0.66
    Activations Density 1.134%

    No Known Activations