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

    Neuronpedia

    Jacobian LensNEW
    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. 1-RES-JB
    11. 21817
    Prev
    Next
    INDEX
    Explanations

    words related to a specific organization or political movement named "Center for American Progress."

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of progressivism

    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
    earth
    -0.78
    pron
    -0.73
    idden
    -0.73
     pronounced
    -0.68
    FACE
    -0.68
     allerg
    -0.68
     pepper
    -0.67
    assic
    -0.67
     tasting
    -0.66
     volcanic
    -0.66
    POSITIVE LOGITS
     Progress
    1.35
    Progress
    1.21
    progress
    1.04
    ivism
    0.97
    ives
    0.95
    eous
    0.83
    achus
    0.76
    alion
    0.73
    ieve
    0.73
     Publishers
    0.73
    Activations Density 0.005%

    No Known Activations