© 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. 10-RES-JB
    11. 2805
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "now."

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of time, particularly the word "now."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     similarity
    -0.56
     heav
    -0.54
     similarities
    -0.54
     Shards
    -0.53
     misfortune
    -0.53
     ZIP
    -0.52
     Heaven
    -0.52
     Eighth
    -0.52
     ozone
    -0.51
     Packs
    -0.51
    POSITIVE LOGITS
    adays
    1.44
    here
    1.28
    abouts
    1.07
    tics
    0.94
    heres
    0.92
    tical
    0.83
    heric
    0.78
    orthy
    0.77
    endi
    0.74
    ledge
    0.73
    Activations Density 0.077%

    No Known Activations