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. 6-RES-JB
    6. 13303
    Prev
    Next
    INDEX
    Explanations

    descriptions of things as "strange"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "strange" and its variations

    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
    cussion
    -0.82
    payers
    -0.78
    bern
    -0.78
    inders
    -0.78
    igate
    -0.75
    vation
    -0.75
    agles
    -0.73
    chen
    -0.72
    amaru
    -0.72
    apers
    -0.71
    POSITIVE LOGITS
     occurrences
    0.97
    ness
    0.87
     coincidence
    0.86
    ly
    0.86
    worldly
    0.83
     twists
    0.82
     twist
    0.79
     assortment
    0.76
     aber
    0.73
    nesses
    0.73
    Activations Density 0.041%

    No Known Activations