© 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. 13725
    Prev
    Next
    INDEX
    Explanations

    expressions of determination or commitment to take action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "do" in various contexts

    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
    uses
    -0.63
    mares
    -0.61
    Rank
    -0.61
    ãĤ¼ãĤ¦ãĤ¹
    -0.58
    antha
    -0.58
    liner
    -0.57
    lights
    -0.57
     CLS
    -0.56
    used
    -0.56
    being
    -0.54
    POSITIVE LOGITS
    oms
    1.03
    omsday
    0.96
    oming
    0.96
    xx
    0.95
    ctr
    0.92
     nothing
    0.91
     away
    0.90
    vet
    0.90
    lez
    0.90
     something
    0.87
    Activations Density 0.113%

    No Known Activations