© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 2890
    Prev
    Next
    INDEX
    Explanations

    mentions of the letter "G" followed by a number, potentially referencing a specific format or coding convention

    oai_token-act-pair · gpt-3.5-turbo

    references to the letter "G" followed by numbers

    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
     htt
    -0.64
     sight
    -0.64
     remotely
    -0.63
     Razor
    -0.63
     lawn
    -0.63
    puter
    -0.62
     ........
    -0.61
     retrospect
    -0.60
     aver
    -0.59
     Grizz
    -0.59
    POSITIVE LOGITS
    oliath
    1.43
    ossip
    1.24
    irlfriend
    1.23
    reet
    1.23
    ourmet
    1.23
    EO
    1.23
    opher
    1.22
    ilded
    1.22
    reetings
    1.21
    ospels
    1.19
    Activations Density 0.045%

    No Known Activations