© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 22654
    Prev
    Next
    INDEX
    Explanations

    time-related words and phrases, particularly events or periods

    oai_token-act-pair · gpt-3.5-turbo

    references to the passage of time and transitions through years or seasons

    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
     Palestin
    -0.70
     Refugees
    -0.67
     {"
    -0.67
    eworld
    -0.67
     Unic
    -0.65
     Redemption
    -0.65
    xual
    -0.63
    edia
    -0.63
     pseudonym
    -0.63
     NCT
    -0.62
    POSITIVE LOGITS
     progressed
    1.21
     progresses
    1.18
     wore
    1.07
     went
    1.03
     goes
    1.02
     dragged
    1.00
     unfolds
    0.95
     wears
    0.95
     unfolded
    0.93
     creeps
    0.90
    Activations Density 0.078%

    No Known Activations