© 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 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. 4325
    Prev
    Next
    INDEX
    Explanations

    phrases related to issuing statements, alerts, endorsements, apologies, and warnings

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "issue" and its variations related to issuing statements, warnings, or alerts

    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
    hov
    -0.90
    uncture
    -0.80
    ovies
    -0.79
    glomer
    -0.73
    ources
    -0.72
    glers
    -0.70
     similarities
    -0.70
    vantage
    -0.68
    antry
    -0.68
    ðĿ
    -0.67
    POSITIVE LOGITS
     apology
    1.28
     statement
    1.25
     Statement
    1.25
     proclamation
    1.20
     warning
    1.18
     ult
    1.07
     summons
    1.07
     apologies
    1.05
     directive
    1.05
    warning
    1.04
    Activations Density 0.123%

    No Known Activations