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. 0-RES-JB
    6. 14201
    Prev
    Next
    INDEX
    Explanations

    phrases related to Native Instruments, a company known for technological development, marketing, and sales of musical products

    oai_token-act-pair · gpt-3.5-turbo

    references to specific companies and individuals in the context of business and investment discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kap
    -0.72
    enic
    -0.69
    $$
    -0.63
    chel
    -0.63
    ugen
    -0.63
    bal
    -0.61
    street
    -0.60
    ļ
    -0.60
    ariat
    -0.60
    RG
    -0.60
    POSITIVE LOGITS
     Instruments
    3.40
     Mous
    1.88
    ydia
    1.48
     Matters
    1.39
    avid
    1.23
     Instrument
    1.03
     Laboratories
    0.91
     Secrets
    0.91
     Aires
    0.89
     Robotics
    0.88
    Activations Density 0.044%

    No Known Activations