© 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. 3-RES-JB
    11. 238
    Prev
    Next
    INDEX
    Explanations

    references to legal and political topics, especially related to freedom of speech and government actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal rights and social justice issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     referen
    -0.51
    uilt
    -0.50
    uable
    -0.48
    çīĪ
    -0.47
    emed
    -0.47
    ĪĴ
    -0.46
     redistributed
    -0.45
    enegger
    -0.45
    uably
    -0.44
    milo
    -0.44
    POSITIVE LOGITS
    terness
    0.44
     PLA
    0.39
    taboola
    0.38
    hesion
    0.38
    min
    0.38
     unprepared
    0.37
    ÂŃ
    0.37
    reach
    0.37
    geries
    0.37
     chars
    0.36
    Activations Density 3.820%

    No Known Activations