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. 7-RES-JB
    6. 22137
    Prev
    Next
    INDEX
    Explanations

    verbs related to spreading or covering an area

    oai_token-act-pair · gpt-3.5-turbo

    elements and phrases related to ongoing problems or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sidx
    -0.85
    iasm
    -0.67
    tu
    -0.66
    uz
    -0.63
    ackers
    -0.62
    ild
    -0.62
     contracting
    -0.60
    iction
    -0.60
     intending
    -0.60
    erm
    -0.60
    POSITIVE LOGITS
     Europe
    0.87
     our
    0.73
     Hollywood
    0.71
     Corona
    0.70
     Mongolia
    0.68
     humankind
    0.68
     Fiji
    0.68
     Sunset
    0.67
     Britain
    0.67
     Charlottesville
    0.66
    Activations Density 0.218%

    No Known Activations