© 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. 10079
    Prev
    Next
    INDEX
    Explanations

    the word 'let'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "let" and its variations indicating an invitation or suggestion to take action

    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
    omething
    -0.72
    ombat
    -0.70
    VERTISEMENT
    -0.69
     Palestin
    -0.68
    Interstitial
    -0.63
    ometimes
    -0.62
     challeng
    -0.58
     disadvant
    -0.58
    é¾įå¥ij士
    -0.56
    natureconservancy
    -0.56
    POSITIVE LOGITS
     me
    1.21
     us
    1.20
    ting
    1.15
    tering
    1.14
    tered
    1.00
    's
    0.99
    ters
    0.99
    itia
    0.95
    \'
    0.78
    ingly
    0.78
    Activations Density 0.023%

    No Known Activations