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

    Neuronpedia

    Jacobian LensNEW
    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. 5771
    Prev
    Next
    INDEX
    Explanations

    proper nouns likely related to geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific cities or geographic locations

    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
     laureate
    -0.72
     VK
    -0.70
     Scythe
    -0.68
     Shard
    -0.67
     Shiv
    -0.66
     maiden
    -0.66
     Eliot
    -0.66
    geist
    -0.65
     Ukip
    -0.65
     Kitty
    -0.64
    POSITIVE LOGITS
    ÃŃn
    1.21
    ña
    1.17
    án
    1.14
    ñ
    1.11
    ÃŃa
    1.10
    ón
    1.09
     Nieto
    1.08
    inho
    1.06
    ño
    1.05
    arez
    1.05
    Activations Density 0.266%

    No Known Activations