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

    Neuronpedia

    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. 4-RES-JB
    11. 20742
    Prev
    Next
    INDEX
    Explanations

    the term "ny" or "NY", particularly when associated with dates or events

    oai_token-act-pair · gpt-3.5-turbo

    references to "New York" or related entities

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

    No Comments

    Negative Logits
    EMP
    -0.83
    Reviewed
    -0.75
    rador
    -0.73
    ENDED
    -0.72
    ENTION
    -0.68
    ModLoader
    -0.68
    IBLE
    -0.66
    ributes
    -0.66
    INGTON
    -0.64
     FEMA
    -0.63
    POSITIVE LOGITS
    mph
    1.02
    acht
    0.95
     Mellon
    0.92
    heter
    0.88
    ny
    0.86
    alty
    0.76
    giene
    0.75
    cling
    0.75
     Giuliani
    0.75
    die
    0.75
    Activations Density 0.011%

    No Known Activations