Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 15244
    Prev
    Next
    INDEX
    Explanations

    references to fruits in a text

    oai_token-act-pair · gpt-3.5-turbo

    references to fruit flies

    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
    ebus
    -0.85
    aution
    -0.82
    isSpecialOrderable
    -0.74
    quickShipAvailable
    -0.70
    orld
    -0.68
     Cancel
    -0.66
     Residential
    -0.64
    awar
    -0.62
    govern
    -0.62
     occupancy
    -0.60
    POSITIVE LOGITS
    cake
    1.45
     juice
    1.31
    fruit
    1.31
    cakes
    1.31
     juices
    1.17
     salad
    1.03
     fruit
    1.01
     Juice
    0.99
    fulness
    0.97
    vine
    0.95
    Activations Density 0.054%

    No Known Activations