© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 24160
    Prev
    Next
    INDEX
    Explanations

    financial and crime-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to financial or legal reporting and inquiries

    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
    agall
    -0.64
     metaphor
    -0.63
    ophers
    -0.63
    astic
    -0.63
    poon
    -0.62
    ieri
    -0.61
    Instance
    -0.60
     analogy
    -0.60
    Dest
    -0.60
    ç¥ŀ
    -0.59
    POSITIVE LOGITS
     sightings
    0.98
     violations
    0.82
     incidents
    0.80
    formance
    0.74
     irregularities
    0.73
    ewitness
    0.71
     failures
    0.70
     inaccur
    0.70
     discrepancies
    0.70
     receipts
    0.70
    Activations Density 0.256%

    No Known Activations