© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 22
    Prev
    Next
    INDEX
    Explanations

    references to different beliefs, laws or teachings in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "according to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     encount
    -0.83
     helicop
    -0.80
     eleph
    -0.69
    ccording
    -0.68
     occas
    -0.65
    uckland
    -0.65
     coh
    -0.64
     exting
    -0.62
     reluct
    -0.60
     gobl
    -0.60
    POSITIVE LOGITS
     to
    0.97
    lly
    0.85
    ly
    0.80
    DragonMagazine
    0.79
     "$:/
    0.73
    inventoryQuantity
    0.70
     thereto
    0.67
    To
    0.67
    LY
    0.66
    Values
    0.65
    Activations Density 0.053%

    No Known Activations