Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 3383
    Prev
    Next
    INDEX
    Explanations

    words related to criminal activities, specifically theft

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to theft

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reynolds
    -0.76
     Zucker
    -0.71
    PRES
    -0.65
     evaluates
    -0.65
     tuned
    -0.65
    enegger
    -0.65
    hel
    -0.63
    etus
    -0.63
    ghan
    -0.63
    ben
    -0.63
    POSITIVE LOGITS
     theft
    3.73
     thefts
    2.91
     Theft
    2.60
     thieves
    2.47
     thief
    2.26
     robbery
    2.07
     stealing
    2.02
     burglary
    1.93
     vandalism
    1.86
     stolen
    1.85
    Activations Density 0.018%

    No Known Activations