© 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. 6-RES-JB
    11. 11798
    Prev
    Next
    INDEX
    Explanations

    phrases related to political or social activism

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of being anti or against something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ding
    -0.97
    cutting
    -0.86
    edin
    -0.83
    nets
    -0.82
    rings
    -0.81
    mable
    -0.79
    alties
    -0.78
    ells
    -0.77
    erick
    -0.77
    accompan
    -0.77
    POSITIVE LOGITS
    opsis
    0.85
    urdue
    0.80
    oxin
    0.79
    iso
    0.76
    ño
    0.73
    henko
    0.73
    Wan
    0.71
    xon
    0.69
    chio
    0.68
    ���
    0.68
    Activations Density 0.060%

    No Known Activations