© 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. 17261
    Prev
    Next
    INDEX
    Explanations

    mentions of violent crimes, particularly sexual assault and torture

    oai_token-act-pair · gpt-3.5-turbo

    references to violent crimes and abuses, particularly sexual violence

    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
    angelo
    -0.78
    hower
    -0.75
    natureconservancy
    -0.71
    heast
    -0.71
     Classic
    -0.70
     Ahead
    -0.69
     Balls
    -0.69
     Horizons
    -0.68
    eus
    -0.68
     Minutes
    -0.68
    POSITIVE LOGITS
     rape
    1.50
     torture
    1.41
     murder
    1.33
     kidnapping
    1.33
     rapes
    1.31
     arson
    1.31
     intimidation
    1.28
     robbery
    1.28
     kidn
    1.27
     imprisonment
    1.27
    Activations Density 0.158%

    No Known Activations