© 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. 9-RES-JB
    11. 22803
    Prev
    Next
    INDEX
    Explanations

    references to specific accomplishments or titles related to sports

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the number of times an athlete has won a championship or award

    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
    hops
    -0.94
    uden
    -0.84
    conom
    -0.77
    speak
    -0.76
    pathy
    -0.70
     else
    -0.68
    ovember
    -0.67
    umm
    -0.67
    lements
    -0.67
    hop
    -0.66
    POSITIVE LOGITS
     winner
    1.09
     Olympic
    1.05
     champ
    1.00
     champion
    1.00
     Olymp
    0.98
     winners
    0.98
     loser
    0.96
     recipient
    0.92
     Pulitzer
    0.92
     Grammy
    0.91
    Activations Density 0.084%

    No Known Activations