© 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. 7-RES-JB
    11. 20730
    Prev
    Next
    INDEX
    Explanations

    adjectives and nouns related to people expressing strong opinions or making a loud noise

    oai_token-act-pair · gpt-3.5-turbo

    references to vocal expressions and the term "vocal."

    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
     Reincarn
    -0.94
    uden
    -0.88
    agher
    -0.85
    roxy
    -0.73
    awaru
    -0.72
    ĸļ
    -0.66
    ysc
    -0.66
     Faw
    -0.65
    busters
    -0.65
    ptives
    -0.65
    POSITIVE LOGITS
    izations
    1.23
     cords
    1.21
    isations
    1.17
     chords
    1.08
    izing
    1.04
    izes
    1.04
    ized
    1.04
    izers
    1.02
    izer
    0.96
    ization
    0.93
    Activations Density 0.032%

    No Known Activations