Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-RES-JB
    6. 7906
    Prev
    Next
    INDEX
    Explanations

    words related to different universities and sports teams, particularly in football

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific geographic locations, particularly states and universities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BOOK
    -0.88
    aird
    -0.74
    pread
    -0.73
    jriwal
    -0.72
    enegger
    -0.70
    osponsors
    -0.69
    renches
    -0.66
    ItemImage
    -0.65
    uterte
    -0.65
    bnb
    -0.64
    POSITIVE LOGITS
     State
    1.27
     Tech
    1.17
     Wildcats
    1.01
     Wesley
    0.99
     University
    0.95
     Valley
    0.93
     Wolver
    0.92
    anova
    0.92
     Athletics
    0.91
     Springs
    0.90
    Activations Density 0.072%

    No Known Activations