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. 11-RES-JB
    6. 19345
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to geographic locations

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Mendoza" and related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     menstru
    -0.69
     backpack
    -0.62
     garn
    -0.60
     subtract
    -0.59
     scaven
    -0.58
     departure
    -0.57
     mainland
    -0.57
    terday
    -0.56
    â̦â̦â̦â̦
    -0.56
     graphic
    -0.55
    POSITIVE LOGITS
    ez
    1.22
    elson
    1.22
    elf
    1.20
    ragon
    1.17
    iola
    1.14
    els
    1.11
    enh
    1.11
    elia
    1.09
    orius
    1.08
    ell
    1.06
    Activations Density 0.112%

    No Known Activations