© 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. 2292
    Prev
    Next
    INDEX
    Explanations

    word sequences indicating preparedness for various hypothetical scenarios

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to hypothetical situations or conditions

    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
     ILCS
    -0.78
    ographed
    -0.65
    hua
    -0.62
     Edited
    -0.62
    knit
    -0.61
     Oxy
    -0.61
    pha
    -0.61
    sort
    -0.60
     Nig
    -0.59
    Pinterest
    -0.58
    POSITIVE LOGITS
     unforeseen
    1.15
     unexpectedly
    1.14
     malf
    1.06
     breach
    1.01
     misfortune
    0.99
     suddenly
    0.95
     breaches
    0.94
     lapse
    0.92
     accidentally
    0.91
     breached
    0.90
    Activations Density 0.351%

    No Known Activations