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. 11-RES-JB
    6. 8180
    Prev
    Next
    INDEX
    Explanations

    references to sports results, player information, and match details

    oai_token-act-pair · gpt-3.5-turbo

    mentions of sports events and performances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Polish
    -0.98
    Äį
    -0.97
    Å¡
    -0.94
    ÅĤ
    -0.92
     Poland
    -0.91
    Ohio
    -0.85
     Kasich
    -0.85
    Romney
    -0.84
     Hispan
    -0.81
     Warsaw
    -0.81
    POSITIVE LOGITS
    elaide
    1.87
     Adelaide
    1.85
     Brisbane
    1.77
     AFL
    1.70
     NRL
    1.70
     Melbourne
    1.67
     Canberra
    1.62
     Sydney
    1.53
     NSW
    1.52
     Queensland
    1.52
    Activations Density 0.479%

    No Known Activations