© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 6695
    Prev
    Next
    INDEX
    Explanations

    words related to organized crime or activities associated with it

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "organized" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PLIED
    -0.81
    ï¸ı
    -0.75
    2019
    -0.69
    gam
    -0.67
    reci
    -0.67
    Enh
    -0.67
    UX
    -0.67
    worth
    -0.65
    gets
    -0.65
    rendered
    -0.64
    POSITIVE LOGITS
    eering
    1.06
     crime
    0.87
     seminars
    0.79
     rallies
    0.78
     marches
    0.78
     labor
    0.78
     protests
    0.78
     crowds
    0.77
     caucuses
    0.77
     gatherings
    0.77
    Activations Density 0.034%

    No Known Activations