© 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. 11248
    Prev
    Next
    INDEX
    Explanations

    dates expressed with "th", "nd", "rd", or "st" suffixes

    oai_token-act-pair · gpt-3.5-turbo

    ordinal indicators related to street names or 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
    =-=-=-=-=-=-=-=-
    -0.71
     Canaver
    -0.65
    Reviewer
    -0.64
    Statistics
    -0.64
    relevant
    -0.63
    ombies
    -0.63
    dies
    -0.62
    zai
    -0.62
    ffect
    -0.62
    eros
    -0.61
    POSITIVE LOGITS
     Avenue
    1.39
     Street
    1.23
     Ave
    1.10
     Floor
    1.05
     avenue
    1.04
     Ward
    0.98
     Century
    0.97
     street
    0.95
     Prec
    0.92
     Degree
    0.92
    Activations Density 0.024%

    No Known Activations