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. 3-RES-JB
    6. 11558
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific terms related to various topics, such as countries, companies, and technologies

    oai_token-act-pair · gpt-3.5-turbo

    references to specific countries or geopolitical entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quartered
    -0.48
    heid
    -0.46
    anwhile
    -0.43
     Supports
    -0.43
    formerly
    -0.43
    guyen
    -0.42
     LM
    -0.38
     southeastern
    -0.38
     Prosper
    -0.38
    headers
    -0.36
    POSITIVE LOGITS
    geist
    0.48
     "$:/
    0.47
     sag
    0.44
    ãĤ§
    0.43
     answ
    0.41
    raph
    0.41
    SW
    0.38
    igans
    0.38
     glue
    0.38
    arten
    0.38
    Activations Density 4.045%

    No Known Activations