© 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. 22684
    Prev
    Next
    INDEX
    Explanations

    time-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to the passage of time, specifically in terms of days and years

    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
    XY
    -0.74
     VID
    -0.70
    acted
    -0.69
    alore
    -0.65
    onis
    -0.65
    ACTED
    -0.65
    ERAL
    -0.60
    ãĥ´ãĤ¡
    -0.60
     exception
    -0.59
    allic
    -0.59
    POSITIVE LOGITS
    chool
    1.05
    creen
    1.02
    hift
    0.93
    pring
    0.91
     ago
    0.87
    cript
    0.84
    iblings
    0.84
    ayers
    0.84
    mith
    0.80
    peed
    0.78
    Activations Density 0.138%

    No Known Activations