© 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. 1-RES-JB
    6. 15922
    Prev
    Next
    INDEX
    Explanations

    phrases where the word "speak" occurs

    oai_token-act-pair · gpt-3.5-turbo

    the verb "speak" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.78
     Valentine
    -0.70
    ueller
    -0.68
    gradation
    -0.63
    1994
    -0.63
    \/\/
    -0.63
    inner
    -0.62
    342
    -0.62
    dating
    -0.62
    iety
    -0.62
    POSITIVE LOGITS
     aloud
    0.94
    voice
    0.90
     Speak
    0.84
    ophone
    0.83
     english
    0.83
    ings
    0.82
     fluent
    0.82
     speak
    0.82
     Chomsky
    0.81
     Mandarin
    0.79
    Activations Density 0.017%

    No Known Activations