© 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. 9-RES-JB
    11. 19850
    Prev
    Next
    INDEX
    Explanations

    phrases that express important information or key points

    oai_token-act-pair · gpt-3.5-turbo

    key phrases related to sources or references in text

    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
    iour
    -0.78
    ãĤ¼ãĤ¦ãĤ¹
    -0.68
    iphate
    -0.66
    incible
    -0.66
    arers
    -0.64
    ampires
    -0.63
    itent
    -0.63
    oided
    -0.62
    itational
    -0.61
    iership
    -0.59
    POSITIVE LOGITS
     excerpts
    1.11
     Politico
    1.01
     comments
    0.99
     POLITICO
    0.97
     remarks
    0.96
     Krugman
    0.95
     paragraphs
    0.95
     statements
    0.94
     interviews
    0.93
     tweets
    0.93
    Activations Density 0.567%

    No Known Activations