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. 6077
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial activities and legal terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of "debt" or "insolvency."

    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
     Kinnikuman
    -0.64
    EStream
    -0.64
     Leilan
    -0.62
     Okinawa
    -0.61
     inventory
    -0.60
     Dow
    -0.60
     LAST
    -0.60
     cropped
    -0.59
     ribbon
    -0.57
     stock
    -0.57
    POSITIVE LOGITS
    ven
    1.32
    ures
    0.98
    ues
    0.89
    uous
    0.86
    urous
    0.84
    VEN
    0.83
    oes
    0.82
    vez
    0.82
    iction
    0.80
    acular
    0.80
    Activations Density 0.008%

    No Known Activations