© 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. 10-RES-JB
    11. 7740
    Prev
    Next
    INDEX
    Explanations

    mentions of "quad" (likely referring to quadcopter or related terms)

    oai_token-act-pair · gpt-3.5-turbo

    references to "quad" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģį
    -0.87
    ãģĦ
    -0.87
    éĹĺ
    -0.71
    terday
    -0.67
    CRIPTION
    -0.67
    CRIP
    -0.64
    UME
    -0.63
    FORE
    -0.62
    ãģı
    -0.62
     Seller
    -0.60
    POSITIVE LOGITS
    rants
    1.29
    rant
    1.25
    cop
    1.13
    raph
    1.12
    rival
    1.10
    rup
    1.09
    rot
    1.05
    ril
    1.03
    rice
    1.00
    rop
    0.94
    Activations Density 0.022%

    No Known Activations