© 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. 3-RES-JB
    6. 23409
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Let" in the text

    oai_token-act-pair · gpt-3.5-turbo

    phrases that start with "Let" followed by a verb or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PLIED
    -0.73
    CLASSIFIED
    -0.71
     holiest
    -0.69
    existent
    -0.68
     cumbers
    -0.66
    Zen
    -0.65
    atana
    -0.65
    ?????-
    -0.64
    POSE
    -0.64
    AGES
    -0.61
    POSITIVE LOGITS
    icia
    0.98
    itia
    0.94
    ting
    0.83
    tered
    0.82
    hetically
    0.80
    tering
    0.78
    winter
    0.75
    chin
    0.72
    iton
    0.71
    ogether
    0.70
    Activations Density 0.024%

    No Known Activations