© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 11681
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication or language proficiency

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "speak" and its variations in context related to communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \/\/
    -0.76
    ueller
    -0.71
    arette
    -0.71
    hews
    -0.70
    gart
    -0.68
    feeding
    -0.68
    arde
    -0.67
    ighed
    -0.67
    pping
    -0.66
    noon
    -0.66
    POSITIVE LOGITS
     fluent
    1.23
     aloud
    1.12
     louder
    1.10
     english
    1.06
     English
    1.04
     volumes
    1.01
     Mandarin
    0.97
     loudly
    0.97
     softly
    0.95
     plainly
    0.94
    Activations Density 0.056%

    No Known Activations