© 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. 8-RES-JB
    11. 10426
    Prev
    Next
    INDEX
    Explanations

    references to civil wars or civil rights

    oai_token-act-pair · gpt-3.5-turbo

    references to civil society and civil rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hungry
    -0.69
    Tree
    -0.68
     Goff
    -0.65
    ï¸ı
    -0.65
    cca
    -0.65
    asus
    -0.63
    HK
    -0.63
    XX
    -0.63
    edin
    -0.62
    è¦ļéĨĴ
    -0.61
    POSITIVE LOGITS
    izational
    1.44
    isations
    1.11
     liberties
    1.08
     servants
    1.04
     disobedience
    1.04
    izing
    1.00
    ised
    0.96
    ization
    0.94
    izes
    0.92
     Liberties
    0.92
    Activations Density 0.024%

    No Known Activations