© 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. 10-RES-JB
    6. 714
    Prev
    Next
    INDEX
    Explanations

    male names, particularly in combination with titles or professions

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and character names in narratives

    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
     VIDEOS
    -0.95
    inventoryQuantity
    -0.88
    iew
    -0.85
    statement
    -0.81
    )))
    -0.80
    videos
    -0.80
    ashington
    -0.80
    Specific
    -0.78
    soType
    -0.78
    ews
    -0.78
    POSITIVE LOGITS
     protagonist
    1.32
     heroine
    1.06
     stranded
    1.04
     kidnapped
    1.00
     aspiring
    0.99
     narrator
    0.98
     detective
    0.97
     adventures
    0.97
     protagonists
    0.95
     discovers
    0.93
    Activations Density 0.604%

    No Known Activations