© 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. 10-RES-JB
    11. 4521
    Prev
    Next
    INDEX
    Explanations

    the phrase "time of year."

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "time of year."

    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
    fml
    -0.77
     Cosponsors
    -0.75
     Marketable
    -0.72
    tein
    -0.68
    BBC
    -0.67
    itsch
    -0.66
     ILCS
    -0.63
    ingo
    -0.63
    berus
    -0.63
    ahime
    -0.62
    POSITIVE LOGITS
     year
    1.12
     day
    1.02
     reckoning
    1.02
     YEAR
    0.90
     month
    0.88
     week
    0.87
    day
    0.83
     night
    0.81
     Year
    0.77
     yr
    0.76
    Activations Density 0.051%

    No Known Activations