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. 836
    Prev
    Next
    INDEX
    Explanations

    names of places or people

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and locations

    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
    perty
    -0.82
    ongyang
    -0.82
     citiz
    -0.69
    etheless
    -0.66
     resil
    -0.66
     pse
    -0.65
     fundament
    -0.64
     unden
    -0.63
     shenan
    -0.63
     glim
    -0.63
    POSITIVE LOGITS
    phia
    0.73
    nery
    0.69
    phant
    0.69
    ibrary
    0.68
    quin
    0.65
    otide
    0.64
     Towers
    0.64
    steen
    0.63
    gow
    0.63
    bill
    0.62
    Activations Density 0.396%

    No Known Activations