© 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. 1-RES-JB
    11. 7131
    Prev
    Next
    INDEX
    Explanations

    words related to politics or power

    oai_token-act-pair · gpt-3.5-turbo

    references to influential figures or concepts associated with wealth or power

    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
    urers
    -0.71
    aded
    -0.71
    EED
    -0.70
     moon
    -0.66
    ģ«
    -0.60
    umn
    -0.60
     Opinion
    -0.59
    cffff
    -0.59
    ivated
    -0.59
     Carbuncle
    -0.59
    POSITIVE LOGITS
    gie
    0.73
    eston
    0.68
    VPN
    0.67
    wx
    0.65
    ãĤ©
    0.63
    elman
    0.62
    yssey
    0.62
    uddin
    0.61
    adelphia
    0.60
    urg
    0.60
    Activations Density 0.000%

    No Known Activations