© 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. 23993
    Prev
    Next
    INDEX
    Explanations

    events or occurrences that happened in the past

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods described as "past" events

    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
    cius
    -0.71
    VALUE
    -0.71
    Graphics
    -0.67
    cloth
    -0.65
    \<
    -0.63
     inhibitors
    -0.62
    olor
    -0.62
    OHN
    -0.62
    pex
    -0.62
    iquid
    -0.60
    POSITIVE LOGITS
     weekend
    1.39
    ebin
    1.22
     week
    1.12
     WEEK
    0.99
     month
    0.95
     afternoon
    0.95
    cture
    0.94
     Weekend
    0.92
     morning
    0.92
     evening
    0.91
    Activations Density 0.044%

    No Known Activations