© 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. 10-RES-JB
    11. 10185
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific names, titles, or concepts like "Wall Street" and "Phoenix Saga."

    oai_token-act-pair · gpt-3.5-turbo

    specific named entities and references to popular culture or significant cultural phenomena

    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
    avorite
    -0.67
     Weston
    -0.59
    ertility
    -0.59
    expensive
    -0.58
    emade
    -0.57
     Guatem
    -0.56
    Natural
    -0.56
    osite
    -0.55
    200000
    -0.54
    romptu
    -0.53
    POSITIVE LOGITS
    »
    1.94
    [/
    1.80
    âĢ
    1.78
    ãĢį
    1.68
    ]'
    1.67
     âĢ
    1.60
    ''
    1.55
    ,''
    1.49
    </
    1.47
    ãĢ
    1.47
    Activations Density 0.666%

    No Known Activations