© 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. 10521
    Prev
    Next
    INDEX
    Explanations

    keywords related to the DACA (Deferred Action for Childhood Arrivals) program

    oai_token-act-pair · gpt-3.5-turbo

    references to the DACA program

    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
    ensible
    -0.84
    sheet
    -0.78
    points
    -0.72
    sch
    -0.71
    aspx
    -0.70
     magnification
    -0.66
    s
    -0.66
    nings
    -0.65
    straight
    -0.65
    held
    -0.64
    POSITIVE LOGITS
    uador
    0.95
    aca
    0.90
    otton
    0.86
    ibo
    0.81
    asa
    0.81
    qua
    0.79
    acas
    0.77
    ourt
    0.77
    illi
    0.76
    ña
    0.76
    Activations Density 0.019%

    No Known Activations