© 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. 0-RES-JB
    11. 11365
    Prev
    Next
    INDEX
    Explanations

    instances of the word "speak"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the action "speak."

    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
     Batt
    -0.62
     Savings
    -0.61
    bush
    -0.60
     PAT
    -0.58
     Fifty
    -0.57
    tons
    -0.55
    thening
    -0.55
     perennial
    -0.55
     Solitaire
    -0.55
     Miner
    -0.54
    POSITIVE LOGITS
     speak
    3.59
    speak
    2.38
     Speak
    2.31
     speaks
    2.01
     speaking
    1.96
     spoke
    1.83
     talk
    1.68
     spoken
    1.60
     testify
    1.50
    speaking
    1.43
    Activations Density 0.011%

    No Known Activations