© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 20515
    Prev
    Next
    INDEX
    Explanations

    words related to prohibitions, bans, restrictions, and forbidden activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to bans and prohibitions

    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
    eah
    -0.87
    prise
    -0.76
    temp
    -0.72
    ensional
    -0.70
    ager
    -0.70
    uin
    -0.69
    tro
    -0.68
    ipel
    -0.68
    ingham
    -0.67
    dress
    -0.67
    POSITIVE LOGITS
     substances
    0.82
    avorite
    0.79
     prohibited
    0.76
     gambling
    0.73
     airspace
    0.72
     Parenthood
    0.70
     banned
    0.68
    ãĤ´ãĥ³
    0.66
     doping
    0.66
     trademarks
    0.65
    Activations Density 0.050%

    No Known Activations