© 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. 8-RES-JB
    11. 3216
    Prev
    Next
    INDEX
    Explanations

    mentions of collective groups of people expressing opinions or being impacted by decisions

    oai_token-act-pair · gpt-3.5-turbo

    references to "the people" in a political context

    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
    inventoryQuantity
    -1.00
    catentry
    -0.94
    Reloaded
    -0.73
    Smith
    -0.71
    ENC
    -0.69
    BALL
    -0.69
    BuyableInstoreAndOnline
    -0.68
    Operation
    -0.68
    CLASSIFIED
    -0.67
    POS
    -0.67
    POSITIVE LOGITS
    hood
    1.03
    folk
    0.91
     uprising
    0.86
    ongs
    0.84
     inhab
    0.81
     revolt
    0.80
    atics
    0.75
    ocracy
    0.74
    ourced
    0.74
    liest
    0.74
    Activations Density 0.078%

    No Known Activations