© 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. 11518
    Prev
    Next
    INDEX
    Explanations

    phrases related to vocal expressions of strong emotions or commands

    oai_token-act-pair · gpt-3.5-turbo

    actions of yelling and shouting in various contexts

    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
    ãĤ¼ãĤ¦ãĤ¹
    -0.82
    tis
    -0.77
    xtap
    -0.76
    20439
    -0.75
    phi
    -0.74
    Flickr
    -0.73
    cephal
    -0.72
    MRI
    -0.71
    folios
    -0.71
    jiang
    -0.67
    POSITIVE LOGITS
     louder
    1.32
     loudly
    1.27
     slogans
    1.17
     aloud
    1.15
     obsc
    1.13
     inco
    1.01
     insults
    1.01
     loud
    1.00
     "#
    0.99
     unint
    0.99
    Activations Density 0.052%

    No Known Activations