© 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. 8-RES-JB
    11. 22412
    Prev
    Next
    INDEX
    Explanations

    terms related to sports offseason

    oai_token-act-pair · gpt-3.5-turbo

    references to the offseason in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bar
    -0.88
    ymes
    -0.79
    ess
    -0.78
    thood
    -0.76
    ourke
    -0.74
    sem
    -0.73
    swick
    -0.73
    nan
    -0.73
    enth
    -0.73
    emet
    -0.72
    POSITIVE LOGITS
     workouts
    1.02
     acquisitions
    1.01
     departures
    0.86
     signings
    0.86
     workout
    0.86
     offseason
    0.85
     exercises
    0.84
     acquisition
    0.81
     evaluations
    0.80
     restructuring
    0.80
    Activations Density 0.036%

    No Known Activations