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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    11. 12539
    Prev
    Next
    INDEX
    Explanations

    sports teams' names and related terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Pittsburgh Penguins and their related context in hockey

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     locality
    -0.72
     Austin
    -0.68
    arag
    -0.67
     Martha
    -0.66
    DERR
    -0.64
     rural
    -0.63
     Montgomery
    -0.63
     Albany
    -0.62
     Berlin
    -0.62
     Quincy
    -0.61
    POSITIVE LOGITS
     Penguins
    2.79
     Canucks
    2.35
     Predators
    2.16
     Sharks
    2.13
     Coyotes
    2.11
     Cavaliers
    2.11
     Sabres
    2.05
     Hurricanes
    2.01
     Flyers
    2.01
     Grizzlies
    1.99
    Activations Density 0.039%

    No Known Activations