© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 491
    Prev
    Next
    INDEX
    Explanations

    instances of the word "using" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "using."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     swe
    -0.71
     relief
    -0.68
     mark
    -0.60
     stands
    -0.59
     tremb
    -0.59
     reneg
    -0.58
     left
    -0.58
     ball
    -0.58
     therm
    -0.57
     affairs
    -0.56
    POSITIVE LOGITS
    using
    4.05
    uses
    2.56
    used
    2.54
    use
    2.28
    usal
    1.98
    USE
    1.77
    users
    1.75
    usable
    1.71
    user
    1.42
    Using
    1.42
    Activations Density 0.009%

    No Known Activations