© 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 EvalsExportsinterp-engineNEWAPI 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. 18119
    Prev
    Next
    INDEX
    Explanations

    the prefix "de-" followed by various words

    oai_token-act-pair · gpt-3.5-turbo

    instances of the prefix "de-" that indicate various forms of removal, reversal, or negation

    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
    uyomi
    -0.94
    ĸļ
    -0.94
     Flavoring
    -0.92
    DragonMagazine
    -0.91
    ORY
    -0.80
    ocene
    -0.78
     Wage
    -0.74
    ramid
    -0.73
     Dynamics
    -0.71
    ulhu
    -0.70
    POSITIVE LOGITS
     Blasio
    1.03
     jour
    1.01
    utsche
    1.00
    arest
    0.99
    activate
    0.98
    jected
    0.97
    activated
    0.95
    uter
    0.94
    legate
    0.93
     facto
    0.93
    Activations Density 0.018%

    No Known Activations