© 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. 8-RES-JB
    11. 8628
    Prev
    Next
    INDEX
    Explanations

    cities and locations

    oai_token-act-pair · gpt-3.5-turbo

    references to major global cities and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idae
    -0.88
    xual
    -0.88
    species
    -0.83
     allowance
    -0.72
    binary
    -0.72
    ctive
    -0.71
    inctions
    -0.71
    Versions
    -0.70
    itives
    -0.70
    hani
    -0.69
    POSITIVE LOGITS
     Paris
    1.21
     London
    1.20
     Shanghai
    1.14
     Cairo
    1.11
     Frankfurt
    1.10
     Cologne
    1.10
     Tokyo
    1.09
     Copenhagen
    1.09
     Osaka
    1.09
     Stras
    1.08
    Activations Density 0.248%

    No Known Activations