© 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. 6452
    Prev
    Next
    INDEX
    Explanations

    organizations and entities related to politics and business

    oai_token-act-pair · gpt-3.5-turbo

    references to specific organizations and entities involved in social or economic contexts

    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
    retty
    -0.58
    while
    -0.53
    izoph
    -0.53
    ovember
    -0.52
    uesday
    -0.51
    onday
    -0.51
    vre
    -0.51
    resents
    -0.49
    Haunted
    -0.49
    bnb
    -0.49
    POSITIVE LOGITS
     to
    1.22
    to
    0.94
     TO
    0.81
     To
    0.76
    To
    0.76
     ta
    0.67
    ¿
    0.64
     thereto
    0.63
     toget
    0.61
    ande
    0.58
    Activations Density 0.428%

    No Known Activations