Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 7992
    Prev
    Next
    INDEX
    Explanations

    natural disasters and accidents

    oai_token-act-pair · gpt-3.5-turbo

    events involving explosions or significant disasters

    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
     Dialogue
    -0.68
    ociate
    -0.67
     dialogue
    -0.67
    leground
    -0.67
     QUEST
    -0.66
     appointments
    -0.66
    ylum
    -0.66
     Preferences
    -0.65
    bnb
    -0.65
     dialog
    -0.64
    POSITIVE LOGITS
     injuring
    1.56
     killing
    1.38
     destroying
    1.20
     wounding
    1.17
     causing
    1.15
     shattering
    1.06
     damaging
    1.05
     inflicting
    1.05
     trapping
    1.04
     injure
    1.03
    Activations Density 0.216%

    No Known Activations