© 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. 0-RES-JB
    11. 13151
    Prev
    Next
    INDEX
    Explanations

    phrases related to formal procedures or processes

    oai_token-act-pair · gpt-3.5-turbo

    references to formal agreements, procedures, or structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pire
    -0.77
    parts
    -0.72
    Spider
    -0.71
    killer
    -0.70
    dragon
    -0.68
    Haunted
    -0.67
     Everywhere
    -0.67
    aston
    -0.66
     Bullets
    -0.65
     Torrent
    -0.65
    POSITIVE LOGITS
     formal
    3.46
     formally
    2.10
     informal
    1.92
     rigorous
    1.41
    ormal
    1.34
     substantive
    1.18
     ceremonial
    1.17
     verbal
    1.10
     official
    1.10
     officially
    1.05
    Activations Density 0.015%

    No Known Activations