© 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. 3534
    Prev
    Next
    INDEX
    Explanations

    specific geographical locations and structures

    oai_token-act-pair · gpt-3.5-turbo

    important geographical and historical landmarks or concepts

    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
    »Ĵ
    -0.83
    etheless
    -0.77
    cedented
    -0.73
    capacity
    -0.71
     pestic
    -0.71
    practice
    -0.67
    energy
    -0.67
    called
    -0.66
    é¾
    -0.66
    storage
    -0.66
    POSITIVE LOGITS
     Museum
    0.95
     Archive
    0.92
     Era
    0.91
     Commission
    0.91
     Massacre
    0.90
     Project
    0.89
     Simulator
    0.89
     Amendments
    0.89
     Act
    0.88
    âĦ¢
    0.88
    Activations Density 0.231%

    No Known Activations