© 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. 11121
    Prev
    Next
    INDEX
    Explanations

    statements emphasizing safety and security as top priorities

    oai_token-act-pair · gpt-3.5-turbo

    statements related to priorities concerning safety and security

    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
    ugh
    -0.73
     satell
    -0.70
    ozyg
    -0.70
     gobl
    -0.70
     dup
    -0.67
     traces
    -0.66
    uge
    -0.66
     prints
    -0.65
     behaved
    -0.65
    ipp
    -0.64
    POSITIVE LOGITS
     priority
    1.64
     paramount
    1.52
     priorities
    1.36
    priority
    1.33
     Priority
    1.13
     overriding
    1.06
     imperative
    1.03
     priorit
    1.01
     cornerstone
    0.99
     foremost
    0.98
    Activations Density 0.304%

    No Known Activations