© 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. 10-RES-JB
    11. 3496
    Prev
    Next
    INDEX
    Explanations

    phrases related to critique or evaluation

    oai_token-act-pair · gpt-3.5-turbo

    indefinite articles and quantifying adjectives that suggest a degree of magnitude or complexity

    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
     equivalents
    -0.77
     advis
    -0.74
    quickShipAvailable
    -0.72
     flashes
    -0.72
    aos
    -0.69
    awei
    -0.67
     guides
    -0.67
     Attend
    -0.66
    cards
    -0.66
     adaptations
    -0.64
    POSITIVE LOGITS
     longstanding
    1.10
     swath
    1.05
     crucial
    1.02
     portion
    1.00
     nonexistent
    0.98
     chunk
    0.98
     hitherto
    0.97
     cherished
    0.97
    iling
    0.96
     handful
    0.96
    Activations Density 0.277%

    No Known Activations