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. 1-RES-JB
    6. 18489
    Prev
    Next
    INDEX
    Explanations

    injured individuals in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to injuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ebook
    -0.74
    cle
    -0.71
    ingen
    -0.70
    gran
    -0.68
    esters
    -0.67
    nom
    -0.67
    gency
    -0.67
    alled
    -0.66
    ellar
    -0.66
    minist
    -0.66
    POSITIVE LOGITS
     injured
    1.07
    lehem
    0.94
    jured
    0.94
     wounded
    0.93
     injuring
    0.87
     injuries
    0.78
     wounding
    0.77
     survivors
    0.76
     bystanders
    0.75
     victims
    0.74
    Activations Density 0.010%

    No Known Activations