© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 9535
    Prev
    Next
    INDEX
    Explanations

    mentions of sports teams, focusing particularly on the Boston Celtics and the New York Knicks

    oai_token-act-pair · gpt-3.5-turbo

    references to basketball teams and players, particularly the Celtics and the Knicks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    shore
    -0.69
     Bord
    -0.66
     Nar
    -0.64
     Bore
    -0.63
    course
    -0.63
    strip
    -0.63
    akeru
    -0.61
    SPONSORED
    -0.60
     puppet
    -0.60
    ryn
    -0.59
    POSITIVE LOGITS
    NBA
    0.91
     Basketball
    0.86
    ockets
    0.83
     basketball
    0.83
    asketball
    0.82
     Celtics
    0.82
    etic
    0.81
     NBA
    0.80
     Pacers
    0.80
    birds
    0.77
    Activations Density 0.136%

    No Known Activations