© 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. 3202
    Prev
    Next
    INDEX
    Explanations

    references to sports teams, leagues, and organizations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sports teams and leagues

    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
    imon
    -0.69
    iHUD
    -0.68
     href
    -0.66
    anan
    -0.63
    aneous
    -0.58
    onne
    -0.57
     Stam
    -0.56
     Nanto
    -0.56
    Weather
    -0.54
    avers
    -0.54
    POSITIVE LOGITS
     fray
    1.47
     fold
    1.29
    uve
    1.03
    elight
    1.02
     ranks
    0.98
     bandwagon
    0.96
     spotlight
    0.92
     altogether
    0.91
     lineup
    0.87
     throne
    0.86
    Activations Density 0.367%

    No Known Activations