© 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. 7173
    Prev
    Next
    INDEX
    Explanations

    dates and events from personal or professional histories

    oai_token-act-pair · gpt-3.5-turbo

    temporal phrases indicating sequence of events

    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
    =-=-=-=-=-=-=-=-
    -0.88
    aptic
    -0.78
    uckland
    -0.78
    =-=-=-=-
    -0.75
    umeric
    -0.75
    vous
    -0.72
    Supp
    -0.72
    lite
    -0.71
    unny
    -0.70
    eyed
    -0.70
    POSITIVE LOGITS
     retiring
    1.51
     joining
    1.49
     graduating
    1.45
     quitting
    1.38
     becoming
    1.34
     marrying
    1.27
     leaving
    1.21
     resign
    1.20
     founding
    1.18
     stint
    1.18
    Activations Density 0.176%

    No Known Activations