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. 22740
    Prev
    Next
    INDEX
    Explanations

    proper names, likely related to politics or individuals in the news

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of individuals and organizations

    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
    ĸļ
    -0.69
     Places
    -0.68
     Thumbnails
    -0.68
     paranormal
    -0.62
    Exper
    -0.61
     Triangle
    -0.60
     Hurricane
    -0.60
     STATS
    -0.60
    ĺħ
    -0.60
    Native
    -0.58
    POSITIVE LOGITS
    anyahu
    0.89
    ovich
    0.86
    addafi
    0.86
    gov
    0.82
    Obama
    0.78
    lopp
    0.76
    oÄŁan
    0.76
    ozy
    0.76
    oval
    0.75
    udeau
    0.75
    Activations Density 0.180%

    No Known Activations