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. 12-RES-JB
    6. 14564
    Prev
    Next
    INDEX
    Explanations

    descriptions of violent incidents, including shootings and robberies

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

    references to individuals in a context involving violence or crime

    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
    ilogy
    -0.88
    pmwiki
    -0.81
    thumbnails
    -0.78
    odes
    -0.76
    endars
    -0.76
    enture
    -0.74
    ramid
    -0.73
    ights
    -0.73
    ibraries
    -0.71
    urrection
    -0.71
    POSITIVE LOGITS
     identified
    1.19
     named
    1.06
     Yose
    1.04
     Edwin
    1.04
     Mohamed
    1.03
     Nguyen
    1.01
     Gregory
    1.00
     Vincent
    1.00
     Timothy
    0.99
     Harold
    0.99
    Activations Density 0.222%

    No Known Activations