© 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. 5733
    Prev
    Next
    INDEX
    Explanations

    phrases related to caution, prevention, or maintenance

    oai_token-act-pair · gpt-3.5-turbo

    negations and phrases indicating avoidance or prevention

    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
     Options
    -0.67
    isSpecialOrderable
    -0.66
    Newsletter
    -0.64
     largeDownload
    -0.64
     congratulations
    -0.63
     Houses
    -0.61
     Kinnikuman
    -0.60
     Cors
    -0.60
     Newsp
    -0.60
     YES
    -0.59
    POSITIVE LOGITS
     accidentally
    1.04
     inadvertently
    1.04
     interfere
    1.01
     disturb
    1.01
     jeopard
    1.01
     undue
    0.98
     unnecessarily
    0.97
     ruin
    0.96
     contam
    0.95
     unintentionally
    0.95
    Activations Density 0.255%

    No Known Activations