© 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. 11-RES-JB
    11. 23
    Prev
    Next
    INDEX
    Explanations

    hyphenated brand names, specifically focusing on instances where "Wal-Mart" is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    references to "Wal-Mart" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     distraction
    -0.75
     distracting
    -0.67
     complement
    -0.61
     abstinence
    -0.59
     distractions
    -0.58
    ^^
    -0.57
     NOW
    -0.57
     adjourn
    -0.56
    Äĩ
    -0.56
     attraction
    -0.54
    POSITIVE LOGITS
    Mart
    1.47
    mart
    1.19
    Hen
    0.85
    street
    0.84
    Street
    0.84
    Mo
    0.80
    Wal
    0.80
    Cola
    0.76
    East
    0.76
    jong
    0.75
    Activations Density 0.034%

    No Known Activations