© 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. 7-RES-JB
    11. 23966
    Prev
    Next
    INDEX
    Explanations

    phrases related to the passage of time

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "passage" in relation to time or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pora
    -0.89
    iversity
    -0.75
     resid
    -0.73
    RAW
    -0.71
    ises
    -0.68
     Columb
    -0.67
    olulu
    -0.67
    ise
    -0.66
    ikarp
    -0.64
    ches
    -0.64
    POSITIVE LOGITS
     passages
    0.82
     aloud
    0.77
    phrase
    0.77
    uality
    0.75
    through
    0.74
     passage
    0.73
    ttes
    0.72
    bill
    0.68
    notes
    0.66
    ahead
    0.64
    Activations Density 0.030%

    No Known Activations