© 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. 0-RES-JB
    6. 13947
    Prev
    Next
    INDEX
    Explanations

    mentions of live events or broadcasts

    oai_token-act-pair · gpt-3.5-turbo

    references to live events or broadcasts

    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
     bag
    -0.68
     rim
    -0.65
     gravity
    -0.64
     jun
    -0.64
     imperial
    -0.64
     bags
    -0.63
    hesis
    -0.62
    zers
    -0.61
    ocol
    -0.60
     piles
    -0.60
    POSITIVE LOGITS
    Live
    4.18
     Live
    2.18
     LIVE
    1.74
    live
    1.71
     live
    1.47
    Living
    1.28
    Stay
    1.17
    Stand
    1.13
    Life
    1.12
    Radio
    1.08
    Activations Density 0.013%

    No Known Activations