© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 11603
    Prev
    Next
    INDEX
    Explanations

    instances of phrases indicating a specific timing or condition/event occurrence

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "when."

    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
    ighed
    -0.77
    hid
    -0.75
    vec
    -0.74
    wered
    -0.74
    oof
    -0.73
    sed
    -0.70
    WER
    -0.69
    gat
    -0.68
    arious
    -0.67
    uren
    -0.67
    POSITIVE LOGITS
     2019
    0.88
    soever
    0.87
     hostilities
    0.78
     2020
    0.76
     2021
    0.75
     2018
    0.74
     reinforcements
    0.72
     tomorrow
    0.71
     expiration
    0.71
     returns
    0.70
    Activations Density 0.226%

    No Known Activations