© 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. 1-RES-JB
    11. 2368
    Prev
    Next
    INDEX
    Explanations

    words related to hibernation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to hibernation, nations, and the Safari web browser

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     artisan
    -0.76
     pse
    -0.75
    riages
    -0.75
     resil
    -0.73
    anooga
    -0.73
    alore
    -0.71
     chall
    -0.70
     submar
    -0.69
    gotten
    -0.68
    thora
    -0.67
    POSITIVE LOGITS
    nation
    1.00
     Freeze
    0.75
    mobile
    0.74
     Norway
    0.74
    Protect
    0.73
    travel
    0.71
    Ice
    0.71
    uits
    0.69
    obil
    0.69
     Safari
    0.69
    Activations Density 0.029%

    No Known Activations