© 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. 3-RES-JB
    11. 23703
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Mist"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Mist" and its variations, suggesting a focus on a specific theme or series

    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
    kefeller
    -0.82
    ggies
    -0.82
    jriwal
    -0.75
    glomer
    -0.71
    CLUS
    -0.68
    itivity
    -0.65
    FORMATION
    -0.65
    versions
    -0.64
    à¼
    -0.64
    encers
    -0.63
    POSITIVE LOGITS
    akes
    0.98
     Mist
    0.94
    Mist
    0.92
    ake
    0.90
    opol
    0.81
    mist
    0.80
    aken
    0.79
    reatment
    0.75
    pell
    0.73
    ussion
    0.72
    Activations Density 0.005%

    No Known Activations