© 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. 10-RES-JB
    11. 17525
    Prev
    Next
    INDEX
    Explanations

    classified information or documents

    oai_token-act-pair · gpt-3.5-turbo

    references to classified information and documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    annis
    -0.76
     Beard
    -0.73
    soDeliveryDate
    -0.72
    alach
    -0.69
     redeemed
    -0.69
    Kay
    -0.67
    tackle
    -0.66
    wolves
    -0.66
    DAY
    -0.66
    raught
    -0.65
    POSITIVE LOGITS
     briefings
    1.41
     information
    1.27
     documents
    1.13
     intel
    1.11
     material
    1.03
     info
    1.03
     briefing
    1.03
     intelligence
    1.03
     INFORMATION
    1.01
     secrets
    0.99
    Activations Density 0.062%

    No Known Activations