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. 4545
    Prev
    Next
    INDEX
    Explanations

    phrases related to locations or entities, specifically "Ipswich" and "Rasmussen"

    oai_token-act-pair · gpt-3.5-turbo

    specific names and terms associated with organizations and geographic locations

    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
    STEM
    -0.80
    士
    -0.75
    Charge
    -0.74
    ctic
    -0.72
     marrow
    -0.68
    Translation
    -0.68
    cies
    -0.66
    WAYS
    -0.65
    arthy
    -0.65
    CHAPTER
    -0.65
    POSITIVE LOGITS
     Ips
    1.28
    ilon
    1.05
    wich
    0.96
     poll
    0.87
     polling
    0.82
    ilateral
    0.76
    ellig
    0.75
     polls
    0.73
    olit
    0.73
    inois
    0.73
    Activations Density 0.009%

    No Known Activations