© 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. 9-RES-JB
    11. 16097
    Prev
    Next
    INDEX
    Explanations

    dates and time indicators

    oai_token-act-pair · gpt-3.5-turbo

    references to specific times or dates in relation to events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eries
    -0.70
    rouse
    -0.67
    ggles
    -0.66
     Ratings
    -0.57
     Holo
    -0.56
     upcoming
    -0.56
     VIDEOS
    -0.54
    Storage
    -0.54
    geries
    -0.53
    MET
    -0.53
    POSITIVE LOGITS
     amid
    0.90
     after
    0.83
    after
    0.79
     because
    0.76
     owing
    0.75
     citing
    0.74
     unilaterally
    0.74
     angered
    0.71
     amidst
    0.67
     fearing
    0.66
    Activations Density 0.251%

    No Known Activations