© 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. 23054
    Prev
    Next
    INDEX
    Explanations

    events or actions related to business deals, acquisitions, changes in ownership, or political movements

    oai_token-act-pair · gpt-3.5-turbo

    key actions or events related to announcements, movements, and group dynamics

    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
    eous
    -0.65
     yourself
    -0.62
    respective
    -0.59
     myself
    -0.58
    orget
    -0.58
     yourselves
    -0.56
    borgh
    -0.56
    é¾įåĸļ士
    -0.56
     Whenever
    -0.54
     chronological
    -0.53
    POSITIVE LOGITS
     theirs
    1.14
     hers
    0.78
     unexpectedly
    0.77
     him
    0.77
    eworks
    0.69
    their
    0.67
    icted
    0.66
     them
    0.66
     overrun
    0.65
    NetMessage
    0.64
    Activations Density 0.543%

    No Known Activations