© 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. 9-RES-JB
    11. 4689
    Prev
    Next
    INDEX
    Explanations

    topics related to social and political issues, such as marijuana industry, climate report, HIV/AIDS initiatives, and immigration laws

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to specific social issues and industries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imately
    -0.61
    aline
    -0.59
    luent
    -0.57
    iguous
    -0.56
    .$
    -0.56
    ilts
    -0.56
     oneself
    -0.56
    oldemort
    -0.55
    [_
    -0.55
     Santos
    -0.55
    POSITIVE LOGITS
     programme
    0.85
     empire
    0.81
     initiative
    0.81
     strategy
    0.80
     program
    0.78
     portfolio
    0.76
     saga
    0.76
     debacle
    0.76
     experiment
    0.72
     alliance
    0.72
    Activations Density 0.726%

    No Known Activations