© 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. 1-RES-JB
    11. 21585
    Prev
    Next
    INDEX
    Explanations

    phrases and names related to a specific person named Maldonado

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named Maldonado

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PLA
    -0.85
    PU
    -0.72
    naire
    -0.69
    ãĤ·ãĥ£
    -0.69
    Sem
    -0.68
    VA
    -0.67
     Gener
    -0.66
    ature
    -0.66
    prime
    -0.65
    SHIP
    -0.65
    POSITIVE LOGITS
     Mald
    1.03
    ersen
    0.97
    romeda
    0.83
    querque
    0.82
    racuse
    0.80
     mathemat
    0.79
    uration
    0.79
     Seym
    0.79
    arus
    0.75
    inav
    0.75
    Activations Density 0.007%

    No Known Activations