© 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. 8-RES-JB
    6. 23842
    Prev
    Next
    INDEX
    Explanations

    dates and events in a text or document

    oai_token-act-pair · gpt-3.5-turbo

    topics related to events and schedules

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Britons
    -0.66
     Australians
    -0.66
     humans
    -0.66
     people
    -0.65
     Europeans
    -0.64
     Americans
    -0.62
     Canadians
    -0.61
     adventurers
    -0.60
     individuals
    -0.59
     climbers
    -0.58
    POSITIVE LOGITS
    inct
    0.59
    ascript
    0.59
    ãĥĩãĤ£
    0.57
    inite
    0.56
    ONSORED
    0.54
    ERO
    0.54
    ãĤ¡
    0.51
    ãĥķãĤ©
    0.51
    ãĤ¦ãĤ¹
    0.51
    ogly
    0.50
    Activations Density 2.013%

    No Known Activations