© 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. 9228
    Prev
    Next
    INDEX
    Explanations

    subtopics related to laws and regulations, particularly ones involving bans and restrictions

    oai_token-act-pair · gpt-3.5-turbo

    topics related to travel restrictions and bans

    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
    Narr
    -0.83
    ospels
    -0.76
     Volunte
    -0.74
    fortune
    -0.73
     Bridgewater
    -0.72
    yth
    -0.70
     chemistry
    -0.70
     Romance
    -0.70
    venture
    -0.70
     romance
    -0.69
    POSITIVE LOGITS
     bans
    1.81
     banning
    1.78
     prohibitions
    1.69
     ban
    1.65
     banned
    1.62
     restrictions
    1.57
     prohibiting
    1.56
     restricting
    1.53
     prohibit
    1.53
     restriction
    1.48
    Activations Density 0.588%

    No Known Activations