© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 523
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "PR"

    oai_token-act-pair · gpt-4-turbo

    phrases related to legal rights, permissions, or copyright

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "PR" or related identifiers

    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
     Roses
    -0.68
    Lago
    -0.68
     Dwarf
    -0.65
     Genesis
    -0.64
     Diablo
    -0.64
     Elves
    -0.63
     Ducks
    -0.63
     Germans
    -0.63
    require
    -0.62
     Mighty
    -0.62
    POSITIVE LOGITS
    ODUCT
    1.47
    ISM
    1.05
    IME
    1.01
    INC
    0.98
    OGR
    0.97
    IZE
    0.94
    udence
    0.91
    ector
    0.91
    OF
    0.90
    unity
    0.83
    Activations Density 0.005%

    No Known Activations