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. 1-RES-JB
    6. 17488
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "pizza"

    oai_token-act-pair · gpt-3.5-turbo

    references to pizza and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uten
    -0.86
    semb
    -0.81
    stadt
    -0.76
    borough
    -0.76
    particip
    -0.74
    byter
    -0.73
    tenance
    -0.73
    uncture
    -0.73
     McDonnell
    -0.70
    olate
    -0.70
    POSITIVE LOGITS
     corrid
    1.03
    !/
    0.78
     CTR
    0.76
    gb
    0.75
    âĿ
    0.74
    atown
    0.73
     Mehran
    0.73
    Enlarge
    0.71
    anches
    0.71
    gencies
    0.69
    Activations Density 0.021%

    No Known Activations