© 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. 10-RES-JB
    11. 18499
    Prev
    Next
    INDEX
    Explanations

    phrases related to criminal activities and police involvement

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of commas in reporting contexts

    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
    izen
    -0.78
    payer
    -0.76
    yt
    -0.71
     <[
    -0.71
    leground
    -0.70
    llor
    -0.70
    omics
    -0.69
    idian
    -0.68
    iri
    -0.68
    obyl
    -0.67
    POSITIVE LOGITS
     according
    1.23
     injuring
    1.19
     prompting
    1.09
     causing
    1.06
     authorities
    1.04
     prosecutors
    1.02
     TMZ
    0.98
     police
    0.97
     wounding
    0.95
    according
    0.94
    Activations Density 0.233%

    No Known Activations