© 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. 9310
    Prev
    Next
    INDEX
    Explanations

    instances of dates, appointments, scheduled events, and historical periods, particularly when introduced with the word "from."

    oai_token-act-pair · gpt-3.5-turbo

    temporal phrases indicating a range of years or dates

    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
    faced
    -0.81
    aqu
    -0.77
    ierrez
    -0.70
    ascript
    -0.68
    hops
    -0.67
    sic
    -0.67
    agy
    -0.66
    Mask
    -0.65
    hai
    -0.65
    important
    -0.65
    POSITIVE LOGITS
     afar
    1.43
     whence
    1.13
     scratch
    1.03
     inception
    0.95
     thence
    0.93
     abroad
    0.87
     conception
    0.84
     within
    0.83
     infancy
    0.82
     outset
    0.82
    Activations Density 0.173%

    No Known Activations