© 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. 9-RES-JB
    11. 19601
    Prev
    Next
    INDEX
    Explanations

    names of sports players, teams, and related terms, along with some proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    names of football players and their associated actions or 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
     Cherokee
    -1.13
     Navajo
    -1.04
     PBS
    -0.98
     Congressional
    -0.94
     legislatures
    -0.88
     statewide
    -0.86
    GOP
    -0.85
     Libertarian
    -0.84
     Native
    -0.84
     Anchorage
    -0.83
    POSITIVE LOGITS
     goalkeeper
    1.18
     striker
    1.17
    inho
    1.14
    iverpool
    1.13
     Guardiola
    1.12
     Liverpool
    1.09
     Tottenham
    1.08
     footballer
    1.08
     midfielder
    1.07
     Everton
    1.05
    Activations Density 0.352%

    No Known Activations