© 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. 6-RES-JB
    11. 8471
    Prev
    Next
    INDEX
    Explanations

    sport-related terms, particularly in the context of contracts and injuries

    oai_token-act-pair · gpt-3.5-turbo

    references to sports contracts and player signings

    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
     ®
    -0.69
    orno
    -0.63
     Lit
    -0.62
     Rowling
    -0.61
     popul
    -0.58
     civilisation
    -0.53
     Paradox
    -0.52
     presenter
    -0.51
     foc
    -0.51
    ÅĤ
    -0.50
    POSITIVE LOGITS
     undrafted
    0.89
    Coach
    0.87
     injury
    0.85
     rookie
    0.85
     teammate
    0.85
     coached
    0.84
     offseason
    0.84
     Rookie
    0.83
    juries
    0.83
    ESPN
    0.81
    Activations Density 1.145%

    No Known Activations