© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 181
    Prev
    Next
    INDEX
    Explanations

    specific technical terms related to fiber optic networks

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resemb
    -0.71
    iHUD
    -0.67
     fronts
    -0.66
     nets
    -0.66
    Ĥª
    -0.65
     trademarks
    -0.65
     Treasurer
    -0.64
     bidding
    -0.64
     dod
    -0.64
     prosecutions
    -0.63
    POSITIVE LOGITS
    ilet
    1.49
    pped
    1.01
    pping
    1.00
    ffee
    0.96
    ggles
    0.93
    asty
    0.89
    othy
    0.87
    fu
    0.85
    ques
    0.85
    oth
    0.85
    Activations Density 0.049%

    No Known Activations