© 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. 2316
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical violence or aggressive behavior

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "beat."

    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
    asel
    -0.68
    ateral
    -0.67
     condem
    -0.66
    orrow
    -0.65
    Import
    -0.64
     pard
    -0.62
    isse
    -0.61
    BuyableInstoreAndOnline
    -0.61
    OPLE
    -0.61
    amera
    -0.60
    POSITIVE LOGITS
    rice
    1.14
    beat
    1.08
    down
    1.07
    boxing
    0.99
    downs
    0.97
    nik
    0.94
    tle
    0.93
    ework
    0.91
    ings
    0.89
    hered
    0.87
    Activations Density 0.045%

    No Known Activations