© 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. 4-RES-JB
    11. 10429
    Prev
    Next
    INDEX
    Explanations

    phrases related to bans and prohibitions

    oai_token-act-pair · gpt-3.5-turbo

    references to legal restrictions or prohibitions

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

    No Comments

    Negative Logits
     dilig
    -0.71
    onica
    -0.69
    ebus
    -0.67
    olars
    -0.66
    auldron
    -0.64
    ilant
    -0.63
    eah
    -0.62
     culmin
    -0.62
     vantage
    -0.61
     GREEN
    -0.61
    POSITIVE LOGITS
    BuyableInstoreAndOnline
    0.78
    à¦
    0.75
    thood
    0.75
     indefinitely
    0.74
    ãĤ´ãĥ³
    0.70
    ãĥīãĥ©ãĤ´ãĥ³
    0.68
    ading
    0.66
     punishable
    0.65
    TRY
    0.64
     Mondays
    0.63
    Activations Density 0.217%

    No Known Activations