© 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. 17735
    Prev
    Next
    INDEX
    Explanations

    keywords related to website posts and articles

    oai_token-act-pair · gpt-3.5-turbo

    references to advice or suggestions in a discussion or article

    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
    Cele
    -0.74
     lining
    -0.72
    window
    -0.71
     Cele
    -0.68
    cele
    -0.65
    goers
    -0.65
     condos
    -0.65
    mouth
    -0.65
    rival
    -0.65
    robe
    -0.64
    POSITIVE LOGITS
     commenter
    1.02
     insightful
    0.95
     commenters
    0.93
     discussion
    0.92
     conject
    0.91
     summar
    0.91
     thesis
    0.90
     article
    0.90
     essay
    0.89
     Discussion
    0.89
    Activations Density 1.088%

    No Known Activations