© 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. 9-RES-JB
    11. 18239
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports events and achievements

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and articles indicating relationships and quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eus
    -0.60
     actors
    -0.59
    webkit
    -0.59
     Gand
    -0.58
    isters
    -0.58
    ··
    -0.56
     dstg
    -0.56
    ersive
    -0.56
    bones
    -0.55
    oids
    -0.55
    POSITIVE LOGITS
     season
    0.99
     preseason
    0.87
    Season
    0.82
     postseason
    0.78
     afternoon
    0.77
    season
    0.75
     career
    0.75
     offseason
    0.74
     outing
    0.73
     schedule
    0.72
    Activations Density 0.030%

    No Known Activations