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. 1-RES-JB
    6. 6025
    Prev
    Next
    INDEX
    Explanations

    phrases related to money, trade, or financial transactions

    oai_token-act-pair · gpt-3.5-turbo

    common conjunctions and transitional phrases indicating connections or actions within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asonic
    -0.48
    microsoft
    -0.47
    \\\\
    -0.44
     [+
    -0.43
    76561
    -0.43
    NetMessage
    -0.42
    ocracy
    -0.41
    Magn
    -0.41
    astical
    -0.41
    tsy
    -0.40
    POSITIVE LOGITS
    itialized
    0.66
     Costs
    0.57
    zik
    0.50
    resy
    0.49
    cknowled
    0.49
    ONSORED
    0.48
    orem
    0.48
    edin
    0.47
    elvet
    0.45
    ĪĴ
    0.44
    Activations Density 0.840%

    No Known Activations