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. 19540
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving fractions and exponents

    oai_token-act-pair · gpt-3.5-turbo

    mathematical symbols and expressions, particularly those related to equations and functions

    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
     chats
    -0.84
     nods
    -0.76
     chat
    -0.75
     cringe
    -0.73
    ettings
    -0.73
    sburg
    -0.72
     heartbeat
    -0.71
     menus
    -0.71
    ::::::::
    -0.69
     safeguards
    -0.68
    POSITIVE LOGITS
    \)
    1.12
    Ïģ
    1.07
     ÎĶ
    1.07
     [(
    1.06
    frac
    1.06
    $$
    1.03
    Î
    1.03
     âĪ
    1.02
    (\
    1.00
    {\
    0.99
    Activations Density 0.240%

    No Known Activations