© 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. 8243
    Prev
    Next
    INDEX
    Explanations

    Keywords related to governance, rules, regulations, laws enforcement, and restrictions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating conditional relationships or options among entities or individuals

    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
     brim
    -0.78
     Tarant
    -0.70
     Doom
    -0.69
     Cotton
    -0.66
     Saturn
    -0.64
    GMT
    -0.64
    GREEN
    -0.63
     Kubrick
    -0.63
     Aden
    -0.62
     cuff
    -0.61
    POSITIVE LOGITS
     pets
    1.09
     caregivers
    0.95
     animals
    0.92
     entities
    0.89
     organizations
    0.87
     organisations
    0.87
     families
    0.85
     grandchildren
    0.84
     bystanders
    0.84
     businesses
    0.82
    Activations Density 0.276%

    No Known Activations