© 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. 20868
    Prev
    Next
    INDEX
    Explanations

    countries

    oai_token-act-pair · gpt-3.5-turbo

    references to countries and their contextual issues

    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
    rious
    -0.77
    hement
    -0.71
    henko
    -0.63
    arsity
    -0.63
     Nicarag
    -0.60
    letes
    -0.59
    zes
    -0.59
    Afee
    -0.58
    Strength
    -0.58
     Dalai
    -0.58
    POSITIVE LOGITS
     classrooms
    0.91
     where
    0.79
     today
    0.77
     illegally
    0.75
     alone
    0.72
     airspace
    0.71
    abouts
    0.69
     jails
    0.68
     countryside
    0.66
     folklore
    0.65
    Activations Density 0.256%

    No Known Activations