© 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. 17694
    Prev
    Next
    INDEX
    Explanations

    mentions of specific city-related entities

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific city

    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
    zees
    -0.94
    etsk
    -0.75
    imilar
    -0.75
    pmwiki
    -0.75
    ioned
    -0.73
    lyak
    -0.72
    uchin
    -0.71
    emonic
    -0.69
    dates
    -0.69
    terday
    -0.69
    POSITIVE LOGITS
    wide
    1.25
    scape
    1.23
     council
    1.18
     skyline
    1.16
     councillor
    1.04
     streets
    1.00
     parks
    0.97
     ordinance
    0.95
     councils
    0.93
     mayor
    0.92
    Activations Density 0.047%

    No Known Activations