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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RES-JB
    11. 17584
    Prev
    Next
    INDEX
    Explanations

    terms related to safety and security, particularly in the context of public health and national interest

    oai_token-act-pair · gpt-3.5-turbo

    terms related to public safety and national security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     confess
    -0.66
    apter
    -0.63
    HEAD
    -0.63
    Ly
    -0.62
    hin
    -0.61
     ellipt
    -0.60
    versions
    -0.59
    verse
    -0.58
     shrink
    -0.58
     cram
    -0.58
    POSITIVE LOGITS
     interests
    1.11
     wellbeing
    0.95
     freedoms
    0.91
     integrity
    0.84
     protections
    0.84
     outwe
    0.83
     rights
    0.83
     Liberties
    0.83
    rity
    0.83
    safety
    0.81
    Activations Density 0.174%

    No Known Activations