© 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. 10951
    Prev
    Next
    INDEX
    Explanations

    mentions of contests, giveaways, and free items

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to contests or giveaways

    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
    azeera
    -0.68
     Afgh
    -0.61
     taxp
    -0.55
    ozyg
    -0.54
    ratom
    -0.54
    ujah
    -0.53
     prolet
    -0.52
    wings
    -0.52
    atomic
    -0.51
     Pastebin
    -0.51
    POSITIVE LOGITS
     akin
    0.56
     triggered
    0.54
     mandated
    0.53
     Pwr
    0.50
     crafted
    0.50
    similar
    0.50
    announced
    0.49
    requisite
    0.49
     handy
    0.48
     similarly
    0.47
    Activations Density 2.096%

    No Known Activations