© 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. 7-RES-JB
    11. 23698
    Prev
    Next
    INDEX
    Explanations

    phrases related to changes in rules, regulations, or guidelines

    oai_token-act-pair · gpt-3.5-turbo

    terms related to governance, rules, and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     teasp
    -0.78
    cffffcc
    -0.69
    opol
    -0.68
    ÃĥÃĤ
    -0.67
    iddles
    -0.66
    married
    -0.65
    arrell
    -0.62
    ãĤ¼ãĤ¦ãĤ¹
    -0.61
    identally
    -0.60
    reason
    -0.60
    POSITIVE LOGITS
     these
    0.83
    uate
    0.70
     this
    0.70
     the
    0.68
     deploying
    0.66
     what
    0.62
     GD
    0.62
     implementing
    0.62
     adopting
    0.60
     HIP
    0.59
    Activations Density 0.621%

    No Known Activations