© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 12433
    Prev
    Next
    INDEX
    Explanations

    mentions of specific college football teams and match scores

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to sports events and statistics

    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
    âĹ¼
    -0.94
     droid
    -0.89
    lyak
    -0.85
     compr
    -0.85
    cffffcc
    -0.81
    ÅĤ
    -0.80
    £
    -0.79
    ertodd
    -0.78
    zhen
    -0.76
    wik
    -0.76
    POSITIVE LOGITS
     Clemson
    1.70
     Heisman
    1.68
     Baylor
    1.63
     NCAA
    1.63
     TCU
    1.62
     LSU
    1.60
     Wildcats
    1.55
     BYU
    1.49
     freshmen
    1.48
     Purdue
    1.47
    Activations Density 0.821%

    No Known Activations