© 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. 11-RES-JB
    11. 17531
    Prev
    Next
    INDEX
    Explanations

    proper nouns that are locations or names of companies or products

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Win" in various contexts

    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
     populated
    -0.69
     gravity
    -0.62
     intestine
    -0.62
     hops
    -0.60
     reservations
    -0.59
     easing
    -0.58
     fault
    -0.58
    ãĥŀ
    -0.56
     moon
    -0.56
     perfection
    -0.55
    POSITIVE LOGITS
    throp
    1.34
    ners
    1.27
    frey
    1.14
    nings
    1.13
    ning
    1.08
    emaker
    1.07
    ston
    1.05
    fred
    1.01
    ters
    0.99
    kel
    0.99
    Activations Density 0.035%

    No Known Activations