© 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. 1-RES-JB
    6. 3875
    Prev
    Next
    INDEX
    Explanations

    specific codes or acronyms, potentially related to technical terms or entities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific entity or designation labeled "Z"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    naissance
    -0.64
     Southeast
    -0.62
     john
    -0.61
    neapolis
    -0.60
     Staples
    -0.59
     pleasure
    -0.59
     Glory
    -0.59
     merry
    -0.58
     spirited
    -0.58
    getic
    -0.58
    POSITIVE LOGITS
    ombie
    1.31
    ombies
    1.28
    ebra
    1.08
    ONE
    1.03
    Z
    1.03
    eta
    1.02
    ERO
    1.02
    oom
    0.97
    oid
    0.95
    oids
    0.95
    Activations Density 0.013%

    No Known Activations