© 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. 20523
    Prev
    Next
    INDEX
    Explanations

    specific references to timing or sequences (e.g., "the moment," "the following year," "the next day")

    oai_token-act-pair · gpt-3.5-turbo

    the word "the" and its variations in different contexts

    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
    thood
    -0.69
    alla
    -0.64
    ictionary
    -0.63
    outs
    -0.63
    ongo
    -0.61
    isi
    -0.60
     Solitaire
    -0.60
    ello
    -0.58
    ania
    -0.57
    oute
    -0.56
    POSITIVE LOGITS
     day
    1.13
     night
    1.08
     moment
    1.05
     same
    1.03
     week
    1.01
     way
    1.01
     morning
    0.99
     quickest
    0.99
    ses
    0.97
     following
    0.96
    Activations Density 0.107%

    No Known Activations