© 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. 8-RES-JB
    11. 11031
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals and their associated political positions or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .","
    -0.66
     decomp
    -0.60
     dece
    -0.59
    ãĥİ
    -0.58
     invention
    -0.56
     approximate
    -0.56
     existence
    -0.55
    200000
    -0.55
     comprom
    -0.55
    $.
    -0.54
    POSITIVE LOGITS
     meanwhile
    1.37
     echoed
    1.09
     countered
    1.02
     congratulated
    0.99
     disagrees
    0.95
     agrees
    0.95
     disagreed
    0.94
     likewise
    0.92
     reacted
    0.90
     applauded
    0.89
    Activations Density 0.487%

    No Known Activations