© 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. 10-RES-JB
    6. 5062
    Prev
    Next
    INDEX
    Explanations

    word sequences related to public speaking and presentations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of communication or speech-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ´ãĥ³
    -0.71
    ocide
    -0.65
    livion
    -0.62
    eless
    -0.58
     bankrupt
    -0.57
    ufact
    -0.56
    apsed
    -0.54
    emate
    -0.54
    save
    -0.53
     1955
    -0.52
    POSITIVE LOGITS
     hopefully
    0.74
    particularly
    0.72
     particularly
    0.72
     Particularly
    0.70
    especially
    0.70
     especially
    0.69
     interestingly
    0.67
     possibly
    0.66
    Especially
    0.65
     maybe
    0.64
    Activations Density 1.314%

    No Known Activations