© 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. 4-RES-JB
    11. 19466
    Prev
    Next
    INDEX
    Explanations

    instances where the concept of time is emphasized, specifically focusing on the word "minute"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "minute" with varying contexts

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

    No Comments

    Negative Logits
    ashtra
    -0.95
     Consortium
    -0.83
    IGH
    -0.79
    ILLE
    -0.75
    INA
    -0.71
     redistributed
    -0.69
    WAR
    -0.67
     CSI
    -0.66
    inav
    -0.66
    atche
    -0.65
    POSITIVE LOGITS
    aneously
    0.84
     livest
    0.77
    parts
    0.74
    aire
    0.73
     Maid
    0.73
    aires
    0.72
    isters
    0.72
     increments
    0.70
    endment
    0.69
    aneous
    0.68
    Activations Density 0.012%

    No Known Activations