© 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 EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 3165
    Prev
    Next
    INDEX
    Explanations

    references to legal actions, especially arrests and warrants

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    occurrences of the word "arrest" and related terms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÃŁ
    -0.64
    ^^^^
    -0.62
    tera
    -0.60
     nutrit
    -0.59
     Squirrel
    -0.57
     Clubs
    -0.55
    opter
    -0.55
    ãĥĥãĥĪ
    -0.54
     kindergarten
    -0.53
     deceive
    -0.52
    POSITIVE LOGITS
     warrant
    1.28
    ees
    1.20
     warrants
    1.14
     Warrant
    1.14
    ee
    1.00
     affidavit
    0.97
    ments
    0.85
    able
    0.83
    oppable
    0.81
    orate
    0.80
    Activations Density 0.071%

    No Known Activations