© 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. 15708
    Prev
    Next
    INDEX
    Explanations

    names starting with "Sav" or "Savior."

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names, particularly related to locations or people associated with the term "Sav"

    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
     slee
    -0.70
    PRES
    -0.69
     inclined
    -0.68
     bom
    -0.68
     locating
    -0.67
     threaded
    -0.65
     proximity
    -0.64
     gravity
    -0.64
     vain
    -0.63
    PRESS
    -0.62
    POSITIVE LOGITS
    Sav
    1.18
     Sav
    1.11
    icz
    1.04
    ille
    0.91
    itri
    0.91
    inelli
    0.90
    annah
    0.89
    azz
    0.88
    ebook
    0.87
    icer
    0.87
    Activations Density 0.002%

    No Known Activations