© 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. 10-RES-JB
    11. 5360
    Prev
    Next
    INDEX
    Explanations

    terms related to social, economic, political, and psychological aspects of various topics

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to economics and political issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sembly
    -0.80
     [|
    -0.77
    gov
    -0.76
    shall
    -0.71
    renheit
    -0.71
     Recomm
    -0.70
    thens
    -0.70
    alin
    -0.70
    lda
    -0.69
     Slowly
    -0.69
    POSITIVE LOGITS
     ramifications
    1.60
     implications
    1.59
     consequences
    1.46
     repercussions
    1.31
     dimension
    1.30
     aspects
    1.29
     aspect
    1.29
     significance
    1.25
     complexities
    1.24
     landscape
    1.23
    Activations Density 0.179%

    No Known Activations