© 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. 10-RES-JB
    11. 19031
    Prev
    Next
    INDEX
    Explanations

    words related to sports standings and points

    oai_token-act-pair · gpt-3.5-turbo

    points and rankings in sports standings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     speeches
    -0.69
     Peck
    -0.68
     bribes
    -0.63
    mob
    -0.62
    ributes
    -0.61
     concess
    -0.60
    obyl
    -0.59
     keynote
    -0.59
    Tube
    -0.58
     accents
    -0.57
    POSITIVE LOGITS
     unbeaten
    1.05
     undefeated
    0.96
     standings
    0.91
     playoff
    0.89
     relegation
    0.83
     ninth
    0.82
     sixth
    0.82
     seventh
    0.81
    behind
    0.78
     lowly
    0.77
    Activations Density 0.206%

    No Known Activations