© 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. 4-RES-JB
    11. 10669
    Prev
    Next
    INDEX
    Explanations

    sports teams names in a specific city

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific sports teams

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

    No Comments

    Negative Logits
    dy
    -0.90
    icator
    -0.87
    edy
    -0.83
    iary
    -0.78
    arb
    -0.77
    APD
    -0.76
    iru
    -0.76
    enz
    -0.75
    lying
    -0.74
    sy
    -0.74
    POSITIVE LOGITS
     Dolphins
    0.88
     Marlins
    0.87
     Gardens
    0.82
    pora
    0.76
    ushi
    0.72
    xtap
    0.71
    ricanes
    0.66
     Beach
    0.65
     Islands
    0.63
     Seasons
    0.63
    Activations Density 0.011%

    No Known Activations