© 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. 4-RES-JB
    6. 10585
    Prev
    Next
    INDEX
    Explanations

    words related to health conditions such as arthritis, joint pain, and fatigue

    oai_token-act-pair · gpt-3.5-turbo

    the pronoun "he" in various contexts

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

    No Comments

    Negative Logits
    hips
    -0.91
     eleph
    -0.70
     GEAR
    -0.69
     Labrador
    -0.61
     domestically
    -0.61
    ãĥ¯
    -0.59
    rador
    -0.59
    enthal
    -0.57
     internationally
    -0.57
     linking
    -0.56
    POSITIVE LOGITS
    isure
    1.10
    ller
    0.99
    lling
    0.96
    ALTH
    0.95
    atre
    0.92
    aven
    0.91
    aton
    0.90
    dule
    0.89
    arth
    0.89
    ather
    0.88
    Activations Density 0.043%

    No Known Activations