© 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. 7-RES-JB
    11. 23928
    Prev
    Next
    INDEX
    Explanations

    warnings and alerts

    oai_token-act-pair · gpt-3.5-turbo

    sections related to warnings and alerts about potential dangers or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aepernick
    -0.78
    Favorite
    -0.72
    iques
    -0.70
    aez
    -0.69
     excuse
    -0.68
    Interview
    -0.66
    MRI
    -0.66
    yard
    -0.66
    athon
    -0.66
    oyer
    -0.65
    POSITIVE LOGITS
     dangers
    1.31
     risks
    1.09
     impending
    1.04
     pitfalls
    0.99
     danger
    0.98
     warnings
    0.93
    danger
    0.93
     hazards
    0.92
     dire
    0.89
     beware
    0.88
    Activations Density 0.152%

    No Known Activations