© 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. 9487
    Prev
    Next
    INDEX
    Explanations

    references to timepieces, specifically watches

    oai_token-act-pair · gpt-3.5-turbo

    references to watches or watch-related topics

    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
    Reviewer
    -0.92
    istically
    -0.84
    ally
    -0.80
     chemotherapy
    -0.65
     Prelude
    -0.65
    ately
    -0.65
     Mayhem
    -0.65
     Masquerade
    -0.64
    EngineDebug
    -0.64
    Enlarge
    -0.63
    POSITIVE LOGITS
    tower
    1.61
    dogs
    1.49
    dog
    1.49
    list
    1.07
    word
    1.06
    face
    1.04
    faces
    1.04
    fulness
    1.02
    lists
    1.02
    maker
    0.98
    Activations Density 0.055%

    No Known Activations