© 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. 9-RES-JB
    11. 16484
    Prev
    Next
    INDEX
    Explanations

    instances where a specific event occurs or a particular situation is described

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating specific situations or instances of events

    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
    agra
    -0.83
    ãĥ´
    -0.82
    alo
    -0.78
    DragonMagazine
    -0.78
    QUI
    -0.77
    ãĤ¨
    -0.77
    ãĤ´ãĥ³
    -0.75
    ãĤ´
    -0.75
    abeth
    -0.74
    aug
    -0.73
    POSITIVE LOGITS
     defendants
    0.97
     perpetrators
    0.90
     attackers
    0.89
     assailants
    0.89
     respondents
    0.87
     defendant
    0.86
     collateral
    0.81
     claimants
    0.81
     perpetrator
    0.81
     individuals
    0.81
    Activations Density 0.331%

    No Known Activations