© 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. 4-RES-JB
    11. 17078
    Prev
    Next
    INDEX
    Explanations

    words related to critical conditions or situations

    oai_token-act-pair · gpt-3.5-turbo

    terms that highlight critical or significant conditions, particularly in the context of urgency or importance

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

    No Comments

    Negative Logits
    alities
    -0.83
     Tycoon
    -0.73
    ries
    -0.72
     Times
    -0.71
     Speedway
    -0.70
    ger
    -0.66
     Thing
    -0.64
    ials
    -0.64
    nar
    -0.63
    itude
    -0.62
    POSITIVE LOGITS
     acclaimed
    0.84
     challenged
    0.79
     injuring
    0.76
     exting
    0.76
     impacting
    0.75
     engaged
    0.74
     wounding
    0.74
    Critical
    0.74
     wounded
    0.73
     minded
    0.72
    Activations Density 0.016%

    No Known Activations