© 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. 6564
    Prev
    Next
    INDEX
    Explanations

    phrases related to catching up or updating on information or activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to "catching up" or to be updated on something

    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
    Hom
    -0.61
    hest
    -0.59
     goose
    -0.59
    aah
    -0.59
    efe
    -0.58
    asus
    -0.57
    bey
    -0.57
    elist
    -0.55
     McMaster
    -0.55
    cock
    -0.55
    POSITIVE LOGITS
     with
    0.81
    olescent
    0.71
     to
    0.68
    grades
    0.68
    ancy
    0.67
     somehow
    0.67
     elsewhere
    0.65
     Dragonbound
    0.64
     again
    0.63
    dress
    0.62
    Activations Density 0.044%

    No Known Activations