© 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. 6-RES-JB
    11. 20694
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Stra" followed by a combination of specific letters

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named "Stra" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gdala
    -0.83
    flies
    -0.73
    è¦ļéĨĴ
    -0.71
     Ashton
    -0.68
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.66
     visitation
    -0.65
     Webster
    -0.64
    ICAN
    -0.64
     GOODMAN
    -0.64
    oleon
    -0.64
    POSITIVE LOGITS
    pping
    1.06
    pped
    1.01
    fing
    1.00
    ights
    0.94
    pper
    0.91
    veland
    0.90
    keye
    0.88
    pling
    0.87
    ppy
    0.85
    ppers
    0.84
    Activations Density 0.028%

    No Known Activations