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. 9-RES-JB
    6. 366
    Prev
    Next
    INDEX
    Explanations

    phrases related to safety and accidents in operational environments

    oai_token-act-pair · gpt-3.5-turbo

    situations or contexts related to unexpected events or hazards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pires
    -0.71
    Untitled
    -0.70
    someone
    -0.65
     itself
    -0.64
     deserves
    -0.64
    Compat
    -0.62
    something
    -0.62
    Merit
    -0.61
     HAS
    -0.61
     Himself
    -0.60
    POSITIVE LOGITS
     abound
    1.03
     plentiful
    0.74
     varying
    0.73
     meanwhile
    0.66
     apiece
    0.65
     vary
    0.64
     clustered
    0.63
     likewise
    0.63
     similarly
    0.62
     prolifer
    0.62
    Activations Density 0.968%

    No Known Activations