© 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. 0-RES-JB
    11. 2077
    Prev
    Next
    INDEX
    Explanations

    mentions of time periods such as "last week" or "last season"

    oai_token-act-pair · gpt-3.5-turbo

    phrases relating to time, specifically the word "last" indicating recent events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omorphic
    -0.75
    hazard
    -0.62
     Appears
    -0.59
    omorph
    -0.58
    1001
    -0.58
    lins
    -0.57
    hm
    -0.56
    telling
    -0.55
    ilic
    -0.55
    ually
    -0.55
    POSITIVE LOGITS
     last
    3.35
     LAST
    2.46
    last
    2.28
    Last
    2.02
     Last
    2.01
     yesterday
    1.82
     earlier
    1.53
     final
    1.41
     previous
    1.23
     next
    1.19
    Activations Density 0.073%

    No Known Activations