© 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. 11-RES-JB
    11. 14451
    Prev
    Next
    INDEX
    Explanations

    statistics related to basketball

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics related to sports performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lans
    -0.80
     Lerner
    -0.74
     Tac
    -0.70
    entanyl
    -0.70
    aird
    -0.69
     fentanyl
    -0.68
     Nar
    -0.67
    vag
    -0.66
     Tuc
    -0.66
     poppy
    -0.66
    POSITIVE LOGITS
     Pacers
    1.31
     basket
    1.26
     dunk
    1.25
     Knicks
    1.24
     rim
    1.23
     Sixers
    1.22
     NBA
    1.21
     baskets
    1.20
     Timberwolves
    1.20
     Lakers
    1.19
    Activations Density 0.669%

    No Known Activations