© 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. 2-RES-JB
    11. 10380
    Prev
    Next
    INDEX
    Explanations

    instances of the word "lest"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "lest" which indicates precaution or consequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gran
    -0.69
    starter
    -0.68
    lee
    -0.67
     Cheong
    -0.67
    ird
    -0.66
    tained
    -0.65
    stood
    -0.65
    venant
    -0.64
    ires
    -0.63
    sword
    -0.63
    POSITIVE LOGITS
     lest
    1.32
    ĸļ
    0.91
     detract
    0.84
    bilt
    0.77
    00200000
    0.77
     fret
    0.76
     avert
    0.76
     apprehens
    0.75
     metic
    0.74
    entimes
    0.74
    Activations Density 0.006%

    No Known Activations