Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 3521
    Prev
    Next
    INDEX
    Explanations

    phrases related to political terms and government structures

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express a hierarchical relationship or ranking among groups or individuals

    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
    mith
    -0.86
    ozo
    -0.78
    hirt
    -0.72
    hift
    -0.71
    HT
    -0.69
    nw
    -0.67
    enegger
    -0.66
    ascript
    -0.66
    411
    -0.65
    4000
    -0.63
    POSITIVE LOGITS
     parcel
    0.86
     file
    0.80
    file
    0.77
     dues
    0.69
     accomplishment
    0.69
    idates
    0.65
     gown
    0.63
     conditioning
    0.62
     testament
    0.62
    rity
    0.61
    Activations Density 0.072%

    No Known Activations