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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 11275
    Prev
    Next
    INDEX
    Explanations

    phrases related to alignment or agreement with certain standards or policies

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express consistency or alignment with policies or principles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lot
    -0.73
    du
    -0.70
    gins
    -0.69
    zon
    -0.68
    close
    -0.65
    abouts
    -0.64
     challeng
    -0.62
    eware
    -0.62
    mouth
    -0.62
    enaries
    -0.62
    POSITIVE LOGITS
     tradition
    0.99
     tenets
    0.98
     norms
    0.98
     ideals
    0.97
     principles
    0.97
     teachings
    0.94
     expectations
    0.92
     traditions
    0.92
     guidelines
    0.92
     reality
    0.91
    Activations Density 0.162%

    No Known Activations