© 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. 13391
    Prev
    Next
    INDEX
    Explanations

    specific mentions of the term "ObamaCare" and related topics like distributors and Harlem

    oai_token-act-pair · gpt-3.5-turbo

    mentions of healthcare policies and distribution issues related to ObamaCare

    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
    ciating
    -1.01
    ifying
    -0.94
    geon
    -0.94
    ified
    -0.86
    IRED
    -0.78
    ier
    -0.76
    imens
    -0.75
    hod
    -0.74
    ded
    -0.73
    kered
    -0.73
    POSITIVE LOGITS
    ments
    0.77
    hovah
    0.76
    SHIP
    0.74
    estinal
    0.70
     absor
    0.70
     ILCS
    0.69
    istries
    0.68
     rul
    0.66
    venants
    0.66
    ptives
    0.66
    Activations Density 0.023%

    No Known Activations