© 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. 8448
    Prev
    Next
    INDEX
    Explanations

    phrases related to tools or equipment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to health, safety, and environmental concerns

    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
    ãĤ¤ãĥĪ
    -0.49
    OTE
    -0.49
    ãĤĮ
    -0.46
    ãĤ®
    -0.45
    ãģĤ
    -0.45
    é¾įå
    -0.45
    ãĤ¯
    -0.44
    æĢ
    -0.44
    ãĤ©
    -0.44
    ãĥĥãĥī
    -0.44
    POSITIVE LOGITS
    merce
    0.62
    fecture
    0.59
     largeDownload
    0.54
    mingham
    0.49
    assment
    0.48
    abama
    0.48
    terness
    0.48
    haar
    0.48
    esson
    0.47
     imperson
    0.47
    Activations Density 2.299%

    No Known Activations