© 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. 3485
    Prev
    Next
    INDEX
    Explanations

    physical locations or events that involve criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    incidents involving violence or crime

    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
    ailable
    -0.72
    stood
    -0.65
    aspers
    -0.62
    Emer
    -0.62
    wx
    -0.61
    ulative
    -0.59
    phabet
    -0.59
    rencies
    -0.58
    particularly
    -0.57
    itatively
    -0.57
    POSITIVE LOGITS
    .[
    1.00
    .]
    0.90
    .</
    0.86
    !.
    0.86
    .(
    0.85
    *.
    0.85
    .;
    0.83
    .*
    0.82
     during
    0.80
    }.
    0.80
    Activations Density 0.650%

    No Known Activations