© 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. 16366
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific person named Marlon

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Lon" or variations of it

    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
    ulative
    -0.78
    displayText
    -0.78
    ORTS
    -0.75
    natureconservancy
    -0.73
     Euph
    -0.72
    ADRA
    -0.69
     Syri
    -0.68
    ħĭ
    -0.67
     Debor
    -0.67
    ¥ŀ
    -0.67
    POSITIVE LOGITS
    ovan
    1.12
    naire
    0.95
    ball
    0.91
    lon
    0.88
    auts
    0.86
    ograph
    0.85
    stal
    0.84
    agne
    0.79
    ius
    0.79
    wood
    0.79
    Activations Density 0.013%

    No Known Activations