© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 11345
    Prev
    Next
    INDEX
    Explanations

    keywords related to closed settings or events

    oai_token-act-pair · gpt-3.5-turbo

    references to private or restricted situations, especially surrounding events or meetings

    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
    Catalog
    -0.84
    ãĥīãĥ©ãĤ´ãĥ³
    -0.82
    ãĤ¼ãĤ¦ãĤ¹
    -0.75
    aire
    -0.73
    onne
    -0.73
    erous
    -0.72
    iage
    -0.71
    arta
    -0.71
     Lov
    -0.71
    Ware
    -0.70
    POSITIVE LOGITS
     shutter
    0.90
     closed
    0.87
     doors
    0.84
     closing
    0.82
     lid
    0.81
     curtains
    0.79
     throttle
    0.79
     exting
    0.78
     closures
    0.76
    closed
    0.76
    Activations Density 0.011%

    No Known Activations