© 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. 3-RES-JB
    6. 23017
    Prev
    Next
    INDEX
    Explanations

    items or events that are being notably recognized or commemorated

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "marked" indicating significant events or characteristics

    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
    ADS
    -0.71
    imates
    -0.69
    rouch
    -0.68
    ersive
    -0.66
     listened
    -0.66
    isance
    -0.66
    adra
    -0.65
    ettel
    -0.64
    halla
    -0.62
    urus
    -0.62
    POSITIVE LOGITS
     marked
    0.77
     milestones
    0.76
    mast
    0.76
    manship
    0.75
     marking
    0.74
     signs
    0.72
    ocument
    0.70
     marks
    0.70
    furt
    0.69
     Twain
    0.69
    Activations Density 0.010%

    No Known Activations