© 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
    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. 2108
    Prev
    Next
    INDEX
    Explanations

    time-related events and sequences

    oai_token-act-pair · gpt-3.5-turbo

    references to time and chronological events

    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
    apest
    -0.81
    liest
    -0.77
    gpu
    -0.72
    taboola
    -0.70
    ãĥ´
    -0.67
    youtu
    -0.67
    Any
    -0.66
    Interstitial
    -0.65
    alogy
    -0.65
    wo
    -0.64
    POSITIVE LOGITS
     however
    1.19
     he
    0.97
     shortly
    0.95
     meanwhile
    0.93
     after
    0.91
     though
    0.88
     when
    0.82
     while
    0.82
     she
    0.81
     another
    0.79
    Activations Density 0.181%

    No Known Activations