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. 11-RES-JB
    6. 11041
    Prev
    Next
    INDEX
    Explanations

    mentions of organized crime

    oai_token-act-pair · gpt-3.5-turbo

    references to organized crime

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    PLIED
    -0.85
    UX
    -0.78
    Ö¼
    -0.74
    ittal
    -0.72
     Carney
    -0.70
    ï¸ı
    -0.66
    Virgin
    -0.65
    2019
    -0.65
    efully
    -0.64
    gets
    -0.64
    POSITIVE LOGITS
    eering
    1.09
     crime
    0.99
     protests
    0.82
     opposition
    0.80
     labor
    0.78
     crowds
    0.77
     marches
    0.77
    arity
    0.77
     rallies
    0.75
     rob
    0.74
    Activations Density 0.059%

    No Known Activations