© 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. 17799
    Prev
    Next
    INDEX
    Explanations

    phrases related to improving efficiency and effectiveness in processes

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to improving efficiency and effectiveness in various processes

    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
    çīĪ
    -0.67
     largeDownload
    -0.67
    itars
    -0.64
    canon
    -0.62
    moon
    -0.62
    actionDate
    -0.61
    ĸļ
    -0.60
    Soul
    -0.57
    ãĤ¦ãĤ¹
    -0.57
    cffffcc
    -0.57
    POSITIVE LOGITS
     litigation
    0.72
     compliance
    0.70
     discretionary
    0.67
     activities
    0.66
     adverse
    0.65
     harm
    0.64
     preventive
    0.64
     punitive
    0.63
     costly
    0.63
     future
    0.62
    Activations Density 0.597%

    No Known Activations