© 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. 2-RES-JB
    11. 23706
    Prev
    Next
    INDEX
    Explanations

    keywords related to computer code and programming languages

    oai_token-act-pair · gpt-3.5-turbo

    highly active video titles or names of content that are labeled as recommended or must-watch items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wcs
    -0.50
    pmwiki
    -0.47
    nen
    -0.42
    yip
    -0.42
     mathemat
    -0.40
    Reviewer
    -0.39
    rawdownloadcloneembedreportprint
    -0.38
    omorphic
    -0.38
    Enlarge
    -0.38
    uchin
    -0.36
    POSITIVE LOGITS
     Accessories
    0.40
     Valkyrie
    0.38
    ignty
    0.35
    uffs
    0.34
     TBA
    0.33
    KK
    0.33
    olesterol
    0.32
     sd
    0.32
     USSR
    0.32
    viks
    0.32
    Activations Density 3.925%

    No Known Activations