© 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. 9-RES-JB
    11. 20841
    Prev
    Next
    INDEX
    Explanations

    words related to loudness or intensity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "loud" and related descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    folios
    -0.77
     Reincarn
    -0.76
    photos
    -0.75
    folio
    -0.74
    eele
    -0.72
    onz
    -0.72
    nesota
    -0.68
    clipse
    -0.68
    utics
    -0.67
    hews
    -0.65
    POSITIVE LOGITS
    mouth
    1.44
    eners
    1.20
    ening
    1.08
    ened
    1.05
     louder
    1.04
    est
    1.02
    ness
    1.00
    ener
    1.00
     voices
    0.99
     noises
    0.98
    Activations Density 0.050%

    No Known Activations