© 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. 21763
    Prev
    Next
    INDEX
    Explanations

    countries or nationalities mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    nationalities or countries referenced in the document

    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
    hid
    -0.83
    oscope
    -0.81
    anse
    -0.79
    ructure
    -0.79
    rex
    -0.77
    phe
    -0.77
    iral
    -0.76
    ording
    -0.73
    allery
    -0.73
    uder
    -0.73
    POSITIVE LOGITS
     counterparts
    1.19
     shores
    1.19
     diplomats
    1.15
     officials
    1.14
     citizens
    1.14
     policymakers
    1.12
     taxpayers
    1.11
     sensibilities
    1.11
     audiences
    1.10
     nationals
    1.09
    Activations Density 0.300%

    No Known Activations