© 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 EvalsExportsinterp-engineNEWAPI 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. 18921
    Prev
    Next
    INDEX
    Explanations

    terms related to government departments and services

    oai_token-act-pair · gpt-3.5-turbo

    terms related to health, community services, and social issues

    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
    psons
    -0.80
     rake
    -0.79
     oranges
    -0.78
     nude
    -0.77
     fools
    -0.77
     skirts
    -0.76
     predetermined
    -0.76
     quo
    -0.75
     gallon
    -0.75
     dried
    -0.74
    POSITIVE LOGITS
     Relations
    1.52
     Policy
    1.42
     Management
    1.39
     Affairs
    1.38
     Resource
    1.38
     Assessment
    1.38
     Evaluation
    1.37
     Research
    1.36
     Studies
    1.35
     Monitoring
    1.35
    Activations Density 0.229%

    No Known Activations