© 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. 11-RES-JB
    11. 14995
    Prev
    Next
    INDEX
    Explanations

    names of political figures and locations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of government officials or authorities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     french
    -0.77
     vacuum
    -0.73
     Europe
    -0.71
     comparable
    -0.71
     colder
    -0.71
     Cologne
    -0.71
     femin
    -0.69
     neoc
    -0.69
     cheese
    -0.68
     chees
    -0.68
    POSITIVE LOGITS
    wana
    1.59
    uku
    1.47
    onga
    1.42
    ulu
    1.42
    atu
    1.41
    yip
    1.41
    angan
    1.40
    amba
    1.34
    anu
    1.32
    arat
    1.30
    Activations Density 0.367%

    No Known Activations