© 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. 9-RES-JB
    11. 13153
    Prev
    Next
    INDEX
    Explanations

    sports team names

    oai_token-act-pair · gpt-3.5-turbo

    references to sports teams or sporting events

    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
     bip
    -0.81
     intrins
    -0.78
     sugg
    -0.75
    behavior
    -0.74
     interpre
    -0.74
     informants
    -0.72
     therap
    -0.71
    Versions
    -0.70
     transformations
    -0.69
    natureconservancy
    -0.69
    POSITIVE LOGITS
     Memphis
    1.40
     Houston
    1.35
     Cincinnati
    1.34
     Philadelphia
    1.34
     Louisville
    1.31
     Minnesota
    1.30
     Pittsburgh
    1.29
     Dallas
    1.29
     Carolina
    1.28
     Miami
    1.28
    Activations Density 0.226%

    No Known Activations