© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 17011
    Prev
    Next
    INDEX
    Explanations

    locations or sports teams, specifically focusing on Miami

    oai_token-act-pair · gpt-3.5-turbo

    references to the city of Miami and its associated sports teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iary
    -0.81
    uably
    -0.79
    ebook
    -0.79
    UGC
    -0.79
    icator
    -0.76
     guiActiveUn
    -0.76
    dy
    -0.75
    sed
    -0.74
    ively
    -0.73
    rd
    -0.73
    POSITIVE LOGITS
     Beach
    1.18
     Gardens
    1.17
     Dolphins
    1.09
     Hurricanes
    0.99
     Marlins
    0.98
     Heat
    0.95
     Herald
    0.90
    ricanes
    0.87
     Lakes
    0.83
     Harbour
    0.81
    Activations Density 0.018%

    No Known Activations