© 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. 9-RES-JB
    6. 5470
    Prev
    Next
    INDEX
    Explanations

    phrases related to the act of using something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "use" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ignt
    -0.62
    hetti
    -0.62
     undertaking
    -0.58
    watching
    -0.57
     Entered
    -0.57
     withd
    -0.57
     behold
    -0.56
     issu
    -0.56
    rats
    -0.56
     Isles
    -0.56
    POSITIVE LOGITS
    fully
    1.16
    FUL
    0.96
     sparing
    0.95
    fulness
    0.91
     caution
    0.90
    ful
    0.88
     discretion
    0.86
     eminent
    0.82
     leverage
    0.81
     phrases
    0.80
    Activations Density 0.116%

    No Known Activations