© 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. 10-RES-JB
    6. 13987
    Prev
    Next
    INDEX
    Explanations

    mentions of different types of prices, including gasoline, house, and book prices

    oai_token-act-pair · gpt-3.5-turbo

    references to the cost and variations in prices, particularly of gasoline and housing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lich
    -0.75
    iverse
    -0.69
    ĨĴ
    -0.65
     skelet
    -0.63
     Identity
    -0.63
    ãĤ¨ãĥ«
    -0.63
    nee
    -0.62
    isexual
    -0.61
    lihood
    -0.61
    actor
    -0.61
    POSITIVE LOGITS
    cape
    1.16
    paces
    1.14
    poons
    1.12
    hare
    1.07
    cale
    1.03
    pring
    1.00
    pace
    0.94
    heet
    0.93
    payers
    0.88
    mith
    0.87
    Activations Density 0.105%

    No Known Activations