© 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. 20467
    Prev
    Next
    INDEX
    Explanations

    words related to restrictions, regulations, and prohibited content

    oai_token-act-pair · gpt-3.5-turbo

    themes related to restrictions and regulations regarding access to various types of content or materials

    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
     Skies
    -0.79
     guts
    -0.72
     jaws
    -0.71
     Cars
    -0.70
     Weeks
    -0.70
     Dogs
    -0.70
     Balls
    -0.68
     Eyes
    -0.68
     Tycoon
    -0.68
     Dreams
    -0.67
    POSITIVE LOGITS
     unrelated
    1.01
     unregulated
    1.01
     nont
    1.00
     inappropriate
    0.99
     undesirable
    0.99
     inaccessible
    0.99
    non
    0.99
     identifiable
    0.98
     questionable
    0.97
     spurious
    0.97
    Activations Density 0.164%

    No Known Activations