© 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. 4715
    Prev
    Next
    INDEX
    Explanations

    sentences related to criminal activity, charges, and legal processes

    oai_token-act-pair · gpt-3.5-turbo
    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
     greatness
    -0.75
    omic
    -0.71
    fulness
    -0.68
    atche
    -0.68
    eor
    -0.68
    zsche
    -0.67
    velt
    -0.66
    inav
    -0.64
    efined
    -0.64
     achieves
    -0.62
    POSITIVE LOGITS
     currently
    1.24
     suing
    1.18
    currently
    1.14
     believed
    1.09
     awaiting
    1.09
     slated
    1.04
     scheduled
    1.03
     presently
    0.99
     now
    0.98
     facing
    0.94
    Activations Density 0.282%

    No Known Activations