© 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. 10-RES-JB
    11. 11268
    Prev
    Next
    INDEX
    Explanations

    timestamps or time-related information

    oai_token-act-pair · gpt-3.5-turbo

    references to specific time periods or temporal phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avorite
    -0.83
    haar
    -0.68
    allas
    -0.65
    mers
    -0.62
     proced
    -0.61
    ternity
    -0.61
    nesday
    -0.61
    matically
    -0.60
    Sund
    -0.60
    raltar
    -0.60
    POSITIVE LOGITS
     of
    0.78
    SPONSORED
    0.66
     Newsweek
    0.62
    of
    0.61
    ,
    0.60
    FTWARE
    0.59
     Neh
    0.58
    bell
    0.58
    cens
    0.57
    ohan
    0.56
    Activations Density 0.064%

    No Known Activations