© 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. 8-RES-JB
    11. 17093
    Prev
    Next
    INDEX
    Explanations

    email-related terms and reminders

    oai_token-act-pair · gpt-3.5-turbo

    references to checking personal information or accounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rawdownloadcloneembedreportprint
    -0.77
    EStreamFrame
    -0.67
    von
    -0.67
    udeb
    -0.63
    ;;
    -0.62
    argument
    -0.62
    BuyableInstoreAndOnline
    -0.62
     Learns
    -0.61
    ranged
    -0.61
    SPONSORED
    -0.60
    POSITIVE LOGITS
     balances
    0.90
     compatibility
    0.81
    atches
    0.80
     validity
    0.78
     boxes
    0.76
     correctness
    0.75
    availability
    0.73
    worthiness
    0.73
    geist
    0.73
     adequ
    0.71
    Activations Density 0.130%

    No Known Activations