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. 8-RES-JB
    6. 16474
    Prev
    Next
    INDEX
    Explanations

    terms related to diverse categories like animals, film cameras, medical records, and weaponry

    oai_token-act-pair · gpt-3.5-turbo

    instances of connected and associated phrases, especially those relating to various subjects and topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ":[{"
    -0.74
    tsky
    -0.73
    tg
    -0.72
    ieve
    -0.69
    IGHTS
    -0.67
    idate
    -0.67
    ocument
    -0.67
    \":
    -0.66
    onday
    -0.66
    iev
    -0.66
    POSITIVE LOGITS
     etc
    0.96
     postage
    0.70
     chewing
    0.66
     elephants
    0.66
     acupuncture
    0.66
     census
    0.65
     narcotics
    0.64
     irrigation
    0.64
     curs
    0.64
     fugitive
    0.63
    Activations Density 0.287%

    No Known Activations