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

    Neuronpedia

    APICircuit 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. 7-RES-JB
    6. 18332
    Prev
    Next
    INDEX
    Explanations

    words related to reservations, such as booking a table at a restaurant or a place in an event

    oai_token-act-pair · gpt-3.5-turbo

    terms related to reservations, particularly in dining or hospitality contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sonian
    -0.82
    onic
    -0.74
    inals
    -0.74
    Republic
    -0.70
    lets
    -0.68
    bath
    -0.68
     Zeus
    -0.67
    board
    -0.67
    matically
    -0.66
    son
    -0.64
    POSITIVE LOGITS
    ellen
    1.01
    eers
    0.96
    ño
    0.88
    iquette
    0.84
    hews
    0.83
    naires
    0.81
    erest
    0.80
    essee
    0.80
    ALS
    0.79
    ews
    0.74
    Activations Density 0.093%

    No Known Activations