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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 21006
    Prev
    Next
    INDEX
    Explanations

    references related to organized crime, gangs, and illegal activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to organized crime and its historical context

    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
    etsy
    -0.98
    NASA
    -0.90
    STEM
    -0.86
     Hawking
    -0.83
     ESA
    -0.82
    ause
    -0.80
     Asus
    -0.79
    Widget
    -0.78
    widget
    -0.77
    fml
    -0.77
    POSITIVE LOGITS
     gangs
    2.10
     gang
    1.85
     mafia
    1.73
     Mafia
    1.71
     underworld
    1.66
     thugs
    1.61
     vigilante
    1.59
     robberies
    1.57
     extortion
    1.56
    gang
    1.55
    Activations Density 0.645%

    No Known Activations