© 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. 3-RES-JB
    11. 23014
    Prev
    Next
    INDEX
    Explanations

    references to a specific commercial brand

    oai_token-act-pair · gpt-3.5-turbo

    instances of the acronym "BL" associated with various contexts or products

    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
    framework
    -0.78
    enegger
    -0.74
    gerald
    -0.73
    tainment
    -0.72
    geist
    -0.70
     Lauder
    -0.70
    oteric
    -0.70
    aeda
    -0.69
    mble
    -0.66
    nor
    -0.65
    POSITIVE LOGITS
    OOD
    1.04
    ACK
    1.00
    OCK
    0.94
    adder
    0.89
    ADE
    0.89
    OUT
    0.88
    ISH
    0.87
    ighting
    0.85
    OGR
    0.85
    OW
    0.84
    Activations Density 0.007%

    No Known Activations