© 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. 8-RES-JB
    11. 7782
    Prev
    Next
    INDEX
    Explanations

    terms related to regulations, policies, and legal frameworks

    oai_token-act-pair · gpt-3.5-turbo

    terms related to governance and policies affecting societal and environmental issues

    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
    >]
    -0.71
     Eggs
    -0.61
     Elijah
    -0.61
    opia
    -0.61
    é¾įåĸļ士
    -0.59
    irlf
    -0.59
    igate
    -0.59
    VIDEO
    -0.58
     Daredevil
    -0.58
     Apostle
    -0.57
    POSITIVE LOGITS
     regimes
    1.07
     interventions
    1.06
     frameworks
    1.06
     mechanisms
    0.96
     policies
    0.95
     budgets
    0.95
     barriers
    0.92
     programmes
    0.89
     pressures
    0.88
     strategies
    0.88
    Activations Density 0.730%

    No Known Activations