© 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. 3427
    Prev
    Next
    INDEX
    Explanations

    rules and regulations or restrictions

    oai_token-act-pair · gpt-3.5-turbo

    rules and regulations

    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
    figure
    -0.71
     mirac
    -0.69
    miah
    -0.67
     CrossRef
    -0.66
    acerb
    -0.65
    framework
    -0.63
     Lyndon
    -0.63
    prototype
    -0.62
    effic
    -0.62
    ortun
    -0.61
    POSITIVE LOGITS
     prohibited
    1.07
     nudity
    1.02
     exceptions
    0.97
     allowable
    0.97
     permitted
    0.96
     prohibits
    0.93
     forbidden
    0.92
    bidden
    0.92
     forbids
    0.91
    iquette
    0.91
    Activations Density 0.905%

    No Known Activations