© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 12537
    Prev
    Next
    INDEX
    Explanations

    keywords related to the DACA program and political discussions surrounding it

    oai_token-act-pair · gpt-3.5-turbo

    references to DACA and the Affordable Care Act (ACA)

    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
    want
    -0.71
    uns
    -0.70
    mind
    -0.69
    court
    -0.68
    angs
    -0.67
    Attempts
    -0.65
     masturbation
    -0.65
     IMAGES
    -0.64
    ches
    -0.64
    ths
    -0.64
    POSITIVE LOGITS
    ACA
    0.97
     recipients
    0.90
     amnesty
    0.78
    è¦ļéĨĴ
    0.75
     DACA
    0.73
    BRE
    0.72
     recipient
    0.71
    oÄŁ
    0.70
     beneficiaries
    0.68
     resc
    0.67
    Activations Density 0.006%

    No Known Activations