© 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. 23089
    Prev
    Next
    INDEX
    Explanations

    the word "Coupe" in various contexts, including car types, sports teams, and news articles

    oai_token-act-pair · gpt-3.5-turbo

    references to "cougars."

    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
    Downloadha
    -1.01
    schild
    -0.92
    é»Ĵ
    -0.81
    66666666
    -0.76
     guiActiveUnfocused
    -0.73
    aceutical
    -0.72
    ngth
    -0.70
    utherford
    -0.68
    icago
    -0.68
    70710
    -0.68
    POSITIVE LOGITS
     Cou
    1.22
    riers
    1.05
    ple
    1.01
    plet
    0.97
    iple
    0.97
    plets
    0.92
    ples
    0.90
    reth
    0.87
    rier
    0.86
    pled
    0.85
    Activations Density 0.006%

    No Known Activations