© 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. 20694
    Prev
    Next
    INDEX
    Explanations

    phrases related to political and governmental contexts, as well as emphasis on specific attributes like being unique, pleasing, or strong

    oai_token-act-pair · gpt-3.5-turbo

    highly descriptive phrases that include commas, indicating complex sentence structures or lists

    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
    ramids
    -0.73
    gow
    -0.72
    izon
    -0.69
    asio
    -0.69
    allery
    -0.68
    adas
    -0.67
    Players
    -0.67
    =/
    -0.67
    rea
    -0.66
     Secrets
    -0.65
    POSITIVE LOGITS
     albeit
    1.39
    albeit
    1.00
     bipartisan
    0.83
     huh
    0.83
     supra
    0.82
     um
    0.81
     unregulated
    0.81
     quasi
    0.80
     colorful
    0.79
     uncomp
    0.78
    Activations Density 0.117%

    No Known Activations