© 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. 2-RES-JB
    11. 12602
    Prev
    Next
    INDEX
    Explanations

    chemical compounds or elements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the abbreviation "Tr" followed by numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     doubling
    -0.72
     Archdemon
    -0.70
     formula
    -0.67
    66666666
    -0.67
     arts
    -0.65
    lihood
    -0.63
    MENTS
    -0.62
     need
    -0.61
     multiplying
    -0.59
     drafting
    -0.59
    POSITIVE LOGITS
    ainer
    1.03
    udeau
    1.00
    izoph
    1.00
    unn
    0.98
    Tr
    0.94
    ilateral
    0.94
    unin
    0.92
    aci
    0.92
    imes
    0.91
    asury
    0.91
    Activations Density 0.008%

    No Known Activations