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. 9006
    Prev
    Next
    INDEX
    Explanations

    names of locations or organizations, specifically those starting with "New"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "New."

    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
     malt
    -0.70
     hurt
    -0.67
     tram
    -0.64
     stall
    -0.63
     kin
    -0.61
     orcs
    -0.61
     lean
    -0.60
     proxies
    -0.60
     FIG
    -0.60
     protein
    -0.60
    POSITIVE LOGITS
    New
    3.46
    new
    2.16
     New
    2.14
    NEW
    2.14
     NEW
    1.72
    Old
    1.51
    Los
    1.37
    NY
    1.27
    Chicago
    1.22
    Philadelphia
    1.20
    Activations Density 0.021%

    No Known Activations