© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 12301
    Prev
    Next
    INDEX
    Explanations

    references to catalogs or listings

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "catalog" and related terms

    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
    yip
    -0.83
    erity
    -0.72
    meric
    -0.67
     Suk
    -0.66
    FP
    -0.66
     ie
    -0.64
    Leave
    -0.64
     Mayo
    -0.64
    imity
    -0.64
    vice
    -0.63
    POSITIVE LOGITS
     catalog
    3.96
     catalogue
    3.35
     Catalog
    2.51
    Catalog
    1.61
     curated
    1.20
     archives
    1.14
     archive
    1.12
     inventory
    1.11
     Catal
    1.08
     repertoire
    1.07
    Activations Density 0.009%

    No Known Activations