Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 24251
    Prev
    Next
    INDEX
    Explanations

    phrases with intense emotions or strong vocal expressions like "screaming" and "yelling"

    oai_token-act-pair · gpt-3.5-turbo

    instances of emotional outbursts or expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idious
    -0.72
    ngth
    -0.71
    patrick
    -0.66
     Brune
    -0.65
    atown
    -0.63
    istine
    -0.63
     Salary
    -0.62
    Private
    -0.61
    htaking
    -0.60
    ItemThumbnailImage
    -0.59
    POSITIVE LOGITS
     louder
    1.21
     loudly
    1.12
     loud
    1.12
     uncontroll
    0.94
     aloud
    0.92
     slogans
    0.88
     plaint
    0.82
     incess
    0.80
     inco
    0.80
     praises
    0.78
    Activations Density 0.329%

    No Known Activations