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. 10-RES-JB
    6. 4018
    Prev
    Next
    INDEX
    Explanations

    expressions related to subscriptions or sign-ups

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude related to subscriptions or sign-ups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾įåĸļ士
    -0.70
    ulhu
    -0.61
    alse
    -0.59
    alter
    -0.59
    zona
    -0.58
    glers
    -0.57
    soDeliveryDate
    -0.57
     Fior
    -0.54
     Dickinson
    -0.54
    kered
    -0.54
    POSITIVE LOGITS
     subscribing
    1.37
     signing
    0.95
     submitting
    0.83
     visiting
    0.76
     downloading
    0.74
     participating
    0.74
     supporting
    0.73
     joining
    0.73
    joining
    0.70
     donating
    0.70
    Activations Density 0.011%

    No Known Activations