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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 23538
    Prev
    Next
    INDEX
    Explanations

    terms related to the topic of DACA (Deferred Action for Childhood Arrivals)

    oai_token-act-pair · gpt-3.5-turbo

    references to the DACA (Deferred Action for Childhood Arrivals) program

    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
    points
    -0.79
    sch
    -0.78
    most
    -0.68
     Grind
    -0.66
    fund
    -0.64
    ensible
    -0.64
    held
    -0.63
     nont
    -0.62
    pipe
    -0.61
    s
    -0.61
    POSITIVE LOGITS
    aca
    1.32
    acas
    1.09
    uador
    1.06
    ibo
    1.00
    asa
    0.87
    iola
    0.87
    aii
    0.85
    otton
    0.83
    ilk
    0.80
    uracy
    0.78
    Activations Density 0.009%

    No Known Activations