© 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 EvalsExportsAPI 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. 6-RES-JB
    11. 7894
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or behaviors of other people

    oai_token-act-pair · gpt-3.5-turbo

    references to actions and permissions involving others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Playoff
    -0.76
    enegger
    -0.69
     Unle
    -0.67
    irst
    -0.67
     finale
    -0.65
     Tycoon
    -0.64
     Notting
    -0.64
     Highlights
    -0.62
     Appropri
    -0.61
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.61
    POSITIVE LOGITS
    worldly
    0.81
    ioch
    0.80
    iris
    0.78
    inois
    0.75
    than
    0.75
     faiths
    0.75
     expend
    0.72
    aband
    0.70
     perspectives
    0.70
     besides
    0.70
    Activations Density 0.450%

    No Known Activations