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. 7228
    Prev
    Next
    INDEX
    Explanations

    sports teams and their standings

    oai_token-act-pair · gpt-3.5-turbo
    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
    %%%%
    -0.75
    iannopoulos
    -0.70
    enter
    -0.68
    hoe
    -0.67
    Demand
    -0.66
    llah
    -0.66
    intosh
    -0.65
    dayName
    -0.64
    itus
    -0.64
    riber
    -0.64
    POSITIVE LOGITS
     undefeated
    1.29
     unbeaten
    1.28
     coached
    1.09
     contenders
    1.06
     favourites
    1.02
     fortunate
    0.99
     eliminated
    0.97
     champions
    0.96
     stocked
    0.95
    efeated
    0.95
    Activations Density 0.146%

    No Known Activations