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. 10-RES-JB
    6. 21098
    Prev
    Next
    INDEX
    Explanations

    dates and specific events listed in a sequential order

    oai_token-act-pair · gpt-3.5-turbo

    references to sports events, specifically losses and victories in matches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     DOD
    -0.71
     FOIA
    -0.68
    FBI
    -0.65
    resist
    -0.64
     ATF
    -0.62
     Garfield
    -0.62
     dy
    -0.61
     FBI
    -0.60
     nonviolent
    -0.59
     Yellowstone
    -0.59
    POSITIVE LOGITS
     qualifiers
    0.85
     unbeaten
    0.85
     whilst
    0.84
     qualifier
    0.83
     onwards
    0.79
     qualification
    0.76
     Fifa
    0.75
     Belfast
    0.75
     opener
    0.74
     Klopp
    0.74
    Activations Density 0.406%

    No Known Activations