© 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. 9-RES-JB
    11. 14762
    Prev
    Next
    INDEX
    Explanations

    warnings or advice to be cautious or attentive towards particular actions, words, or situations

    oai_token-act-pair · gpt-3.5-turbo

    language related to caution and carefulness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    upon
    -0.70
    lishes
    -0.67
     satisfaction
    -0.65
    ono
    -0.63
    albeit
    -0.63
     settled
    -0.63
    IRE
    -0.62
     unified
    -0.61
    bard
    -0.60
    cible
    -0.60
    POSITIVE LOGITS
     lest
    1.04
     pitfalls
    0.84
    Avoid
    0.73
    é¾įå
    0.72
    çĭ
    0.69
     spoilers
    0.68
     beware
    0.68
     interpreting
    0.67
     Yen
    0.67
    esson
    0.65
    Activations Density 0.158%

    No Known Activations