© 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. 3446
    Prev
    Next
    INDEX
    Explanations

    mentions of panic or panic-inducing situations

    oai_token-act-pair · gpt-3.5-turbo

    words related to panic or anxiety

    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
    elman
    -0.73
     LLP
    -0.69
     acquaintance
    -0.66
    oven
    -0.66
    neau
    -0.65
     Equality
    -0.65
    urden
    -0.64
    esan
    -0.64
    roots
    -0.64
    omething
    -0.63
    POSITIVE LOGITS
     inducing
    0.99
    quit
    0.97
     panic
    0.91
     vomiting
    0.85
     uncontroll
    0.85
    panic
    0.84
     disorder
    0.82
     Panic
    0.82
     Disorder
    0.81
     epile
    0.79
    Activations Density 0.060%

    No Known Activations