© 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. 15370
    Prev
    Next
    INDEX
    Explanations

    names, especially those starting with the letter "M"

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, particularly those with the prefix "Mike" or "Michael"

    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
    raped
    -0.86
    SPONSORED
    -0.76
    lishes
    -0.74
    itiveness
    -0.70
     Reconstruction
    -0.68
    uously
    -0.66
    ulhu
    -0.66
    yip
    -0.65
    FU
    -0.64
    ancers
    -0.64
    POSITIVE LOGITS
    opol
    0.71
    ãĤ±
    0.70
    Ń·
    0.70
    chen
    0.68
     reck
    0.64
    adelphia
    0.62
    ahn
    0.61
    olog
    0.61
     Brass
    0.60
     escal
    0.59
    Activations Density 0.274%

    No Known Activations