© 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. 12-RES-JB
    11. 3394
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports injuries and player status updates

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    information related to player injuries and their impact on game participation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    ĸļ
    -0.99
    yip
    -0.87
    htaking
    -0.85
    anchester
    -0.76
    luaj
    -0.76
    hire
    -0.75
    ndum
    -0.73
    ADRA
    -0.72
    Mill
    -0.72
    hovah
    -0.71
    POSITIVE LOGITS
     questionable
    1.22
     sidelined
    1.15
     doubtful
    1.12
     sore
    1.09
     strained
    1.08
     stret
    1.07
     practiced
    1.06
     bruised
    1.03
     MRI
    1.00
     probable
    0.98
    Activations Density 0.294%

    No Known Activations