© 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. 10-RES-JB
    11. 13823
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "sometimes."

    oai_token-act-pair · gpt-3.5-turbo

    the frequent use of the word "sometimes."

    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
    olitan
    -0.95
    mson
    -0.91
    zag
    -0.89
    rats
    -0.79
    ongyang
    -0.77
    ophy
    -0.75
    achus
    -0.74
    iem
    -0.74
    iak
    -0.74
    edIn
    -0.73
    POSITIVE LOGITS
     referred
    0.99
    hift
    0.89
    entimes
    0.89
     mistaken
    0.87
     even
    0.86
    theless
    0.82
     glimps
    0.81
     tempted
    0.81
     called
    0.81
     conflicting
    0.80
    Activations Density 0.039%

    No Known Activations