© 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. 7042
    Prev
    Next
    INDEX
    Explanations

    mentions of specific dates and locations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific events, locations, or meetings involving notable individuals

    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
    76561
    -0.75
    govtrack
    -0.71
    ãĥĥãĥī
    -0.71
     untold
    -0.71
    ¥µ
    -0.59
     hadn
    -0.56
    £ı
    -0.56
    etheless
    -0.56
     dearly
    -0.56
    terror
    -0.56
    POSITIVE LOGITS
     REUTERS
    1.02
     Photographer
    0.88
     Thomson
    0.87
     ©
    0.86
     Credit
    0.86
     Reuters
    0.83
     during
    0.78
     Feb
    0.74
     illustration
    0.74
     October
    0.74
    Activations Density 0.233%

    No Known Activations