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. 6-RES-JB
    6. 22143
    Prev
    Next
    INDEX
    Explanations

    the name "Carlo" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Carlo"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    manship
    -0.85
    imental
    -0.75
    icles
    -0.75
    ICLE
    -0.74
    orship
    -0.71
    iments
    -0.70
    glass
    -0.69
    orial
    -0.68
    chell
    -0.67
    uality
    -0.65
    POSITIVE LOGITS
    zzi
    1.14
    pper
    1.01
    fty
    1.00
    zzle
    0.97
    ppy
    0.95
    ven
    0.93
    oping
    0.90
    tto
    0.88
    pping
    0.88
    ppe
    0.87
    Activations Density 0.020%

    No Known Activations