© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 1593
    Prev
    Next
    INDEX
    Explanations

    instances of disciplinary actions or penalties being taken against individuals

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to disciplinary actions involving suspensions and fines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defic
    -0.68
     mur
    -0.65
    natureconservancy
    -0.62
    azon
    -0.61
    NetMessage
    -0.61
    yip
    -0.58
     seams
    -0.57
    apest
    -0.57
     appar
    -0.56
    ãĤ¨
    -0.55
    POSITIVE LOGITS
     indefinitely
    0.98
     by
    0.85
     for
    0.78
    hirt
    0.75
     permanently
    0.71
     $
    0.71
     twice
    0.69
     probation
    0.68
     Parenthood
    0.67
     pending
    0.66
    Activations Density 0.167%

    No Known Activations