© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 7833
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "time" with high activation values

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to "a time"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avorite
    -0.92
    uctions
    -0.74
    inav
    -0.67
    ging
    -0.67
    deals
    -0.64
     chances
    -0.64
     Hits
    -0.63
    ussions
    -0.62
    emort
    -0.60
    ipation
    -0.59
    POSITIVE LOGITS
    frame
    0.79
    zone
    0.78
    frames
    0.73
    女
    0.72
    neck
    0.72
    lot
    0.70
    è¦ļéĨĴ
    0.70
    glass
    0.70
    pring
    0.70
    Variable
    0.69
    Activations Density 0.019%

    No Known Activations