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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 5587
    Prev
    Next
    INDEX
    Explanations

    words related to specific types of hazards and dangers in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    end-of-text markers signaling the completion of a text segment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cale
    -0.99
    uden
    -0.83
    terday
    -0.79
    yip
    -0.77
    ighthouse
    -0.77
    auga
    -0.76
    epad
    -0.76
    aukee
    -0.74
    everal
    -0.74
    ulu
    -0.73
    POSITIVE LOGITS
     registrations
    0.92
     makers
    0.92
     replacements
    0.90
     populations
    0.90
     owners
    0.85
     sizes
    0.85
     movements
    0.85
     sites
    0.84
     casualties
    0.83
     associations
    0.83
    Activations Density 0.608%

    No Known Activations