© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 20681
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the passage of time

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" and its variants in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceFile
    -0.74
    xual
    -0.71
    minecraft
    -0.64
    aila
    -0.64
     Merrill
    -0.60
    uge
    -0.60
    etsy
    -0.57
    olkien
    -0.56
    Band
    -0.55
    sth
    -0.55
    POSITIVE LOGITS
    ciating
    1.01
     Tomorrow
    0.86
     2024
    0.80
     sunrise
    0.76
     tomorrow
    0.76
     2019
    0.74
     2030
    0.73
    days
    0.72
     2050
    0.70
    ovember
    0.70
    Activations Density 0.121%

    No Known Activations