© 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. 3206
    Prev
    Next
    INDEX
    Explanations

    references to gardens and gardening

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "gard" and its variations, likely relating to a specific context or subject

    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
    uyomi
    -0.63
    phrine
    -0.63
    ting
    -0.60
     favoring
    -0.58
     Heck
    -0.57
    urrent
    -0.57
     AMA
    -0.56
    pson
    -0.56
     Vietnam
    -0.56
     VP
    -0.56
    POSITIVE LOGITS
    ener
    1.28
    llan
    1.13
    yne
    1.02
    ening
    1.02
    endale
    0.96
    inia
    0.96
    iner
    0.93
    ev
    0.91
    aret
    0.88
    ens
    0.85
    Activations Density 0.032%

    No Known Activations