© 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. 24444
    Prev
    Next
    INDEX
    Explanations

    phrases related to time duration

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods and their durations

    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
    ahime
    -0.72
     Technologies
    -0.71
    =-=-=-=-=-=-=-=-
    -0.70
    advertisement
    -0.70
    advertising
    -0.64
    rics
    -0.63
    PsyNetMessage
    -0.62
    acl
    -0.62
    enburg
    -0.62
    Bey
    -0.62
    POSITIVE LOGITS
     LONG
    1.43
     long
    1.40
    long
    1.20
     Long
    0.92
    Long
    0.92
     round
    0.82
     longer
    0.81
    days
    0.78
     length
    0.73
    Short
    0.73
    Activations Density 0.049%

    No Known Activations