© 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. 10-RES-JB
    11. 13565
    Prev
    Next
    INDEX
    Explanations

    numbers representing the results of sports games

    oai_token-act-pair · gpt-3.5-turbo

    statistics and numerical performance metrics related to sports teams

    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
    igmat
    -0.82
    actionDate
    -0.80
    aste
    -0.79
    detail
    -0.72
    ancer
    -0.71
    rophe
    -0.69
    etus
    -0.68
    irit
    -0.67
    wered
    -0.65
    ozy
    -0.64
    POSITIVE LOGITS
     outings
    1.51
     seasons
    1.35
     appearances
    1.33
     games
    1.30
     contests
    1.24
     matchups
    1.20
     meetings
    1.14
     editions
    1.13
     trips
    1.12
     exhibitions
    1.08
    Activations Density 0.068%

    No Known Activations