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

    Neuronpedia

    Jacobian LensNEW
    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. 11-RES-JB
    11. 14944
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Let"

    oai_token-act-pair · gpt-3.5-turbo

    the imperative form of the verb "let."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omething
    -0.76
    ombat
    -0.65
    creen
    -0.64
    ometimes
    -0.62
    VERTISEMENT
    -0.62
    hots
    -0.58
     promot
    -0.56
     Palestin
    -0.56
    mith
    -0.55
    ystem
    -0.55
    POSITIVE LOGITS
    's
    1.26
     me
    1.18
     us
    1.14
    ting
    1.10
    itia
    1.03
    tering
    0.98
    ters
    0.97
    ÃŃs
    0.93
    tered
    0.89
    ´
    0.81
    Activations Density 0.026%

    No Known Activations