© 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 EvalsExportsinterp-engineNEWAPI 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. 13608
    Prev
    Next
    INDEX
    Explanations

    phrases related to time, specifically the following day

    oai_token-act-pair · gpt-3.5-turbo

    instances and repetition of the word "next," especially in relation to timeframes

    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
    phasis
    -0.73
    bia
    -0.72
    zik
    -0.71
    ãĥĥãĥĪ
    -0.70
    udeau
    -0.70
    roid
    -0.69
    zech
    -0.66
    Trend
    -0.66
    licts
    -0.65
    anamo
    -0.65
    POSITIVE LOGITS
     morning
    1.88
     day
    1.88
     afternoon
    1.66
     evening
    1.64
     night
    1.59
     week
    1.46
     weekend
    1.34
     month
    1.34
     year
    1.24
     DAY
    1.22
    Activations Density 0.073%

    No Known Activations