© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 21558
    Prev
    Next
    INDEX
    Explanations

    time-related expressions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate timelines or references to time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tale
    -0.57
     Blind
    -0.53
     proverb
    -0.53
     fingerprint
    -0.53
    advertisement
    -0.52
     Valkyrie
    -0.52
     ect
    -0.52
    itiz
    -0.51
    dress
    -0.51
    REF
    -0.51
    POSITIVE LOGITS
     soon
    1.43
    soon
    1.03
     Soon
    0.99
    Soon
    0.93
    late
    0.92
     shortly
    0.80
    mid
    0.80
    near
    0.80
    Later
    0.76
    early
    0.75
    Activations Density 0.057%

    No Known Activations