© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-RES-JB
    11. 886
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or policy frameworks

    oai_token-act-pair · gpt-3.5-turbo

    references to legislative provisions or sections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     frivol
    -0.77
    ascus
    -0.72
    76561
    -0.62
     gor
    -0.62
     vulner
    -0.61
     enthusi
    -0.61
    isma
    -0.60
    adin
    -0.59
     distur
    -0.59
     audiences
    -0.58
    POSITIVE LOGITS
    neath
    1.59
    stood
    1.36
    stand
    1.36
    mining
    1.27
    graduate
    1.26
    lying
    1.25
    cover
    1.23
    grad
    1.11
    statement
    1.11
    standing
    1.08
    Activations Density 0.036%

    No Known Activations