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. 8-RES-JB
    6. 21334
    Prev
    Next
    INDEX
    Explanations

    places and situations related to criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    incidents involving crime or violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osponsors
    -0.74
    ":"/
    -0.74
    assadors
    -0.73
    ichever
    -0.72
    natureconservancy
    -0.70
    DragonMagazine
    -0.70
    ¯¯¯¯¯¯¯¯
    -0.67
    channelAvailability
    -0.64
    nav
    -0.63
    -)
    -0.63
    POSITIVE LOGITS
     injuring
    0.99
     illegally
    0.95
     accidentally
    0.93
     allegedly
    0.92
     raping
    0.87
     undet
    0.85
     unlawfully
    0.84
     robbery
    0.82
     inappropriately
    0.82
     improperly
    0.81
    Activations Density 0.499%

    No Known Activations