© 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. 6-RES-JB
    11. 2916
    Prev
    Next
    INDEX
    Explanations

    lists of items or options

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the addition of new elements or features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Consumer
    -0.77
    CBC
    -0.72
    VM
    -0.70
    Application
    -0.70
    Business
    -0.65
    Returns
    -0.64
    ardless
    -0.62
    2019
    -0.62
    SHARE
    -0.62
    Compare
    -0.62
    POSITIVE LOGITS
     flair
    0.96
     layer
    0.95
     layers
    0.92
     thereto
    0.87
     reinforcements
    0.83
    endum
    0.79
     insult
    0.77
     suffix
    0.73
     dots
    0.73
     additional
    0.72
    Activations Density 0.203%

    No Known Activations