© 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. 0-RES-JB
    11. 8340
    Prev
    Next
    INDEX
    Explanations

    words related to optimization or minimization

    oai_token-act-pair · gpt-3.5-turbo

    variations of the suffix "imal."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     torch
    -0.64
     staff
    -0.64
     parent
    -0.62
     sibling
    -0.61
     subpoen
    -0.60
     cloak
    -0.60
     drag
    -0.57
     sister
    -0.57
     homophobic
    -0.57
     Newfoundland
    -0.56
    POSITIVE LOGITS
    imal
    4.65
    imum
    2.08
    ima
    1.41
    imo
    1.40
    imus
    1.39
    imize
    1.34
    imens
    1.28
    ims
    1.18
    imi
    1.14
    imen
    1.14
    Activations Density 0.004%

    No Known Activations