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. 6-RES-JB
    6. 4520
    Prev
    Next
    INDEX
    Explanations

    words related to volume or loudness

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "loud" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    folios
    -0.88
    akeru
    -0.81
    folio
    -0.75
     Jacobs
    -0.69
     Peb
    -0.67
    hews
    -0.66
     Reincarn
    -0.66
    istry
    -0.66
     Higgins
    -0.66
    utics
    -0.65
    POSITIVE LOGITS
    mouth
    1.22
     louder
    1.20
    eners
    1.03
     loud
    1.01
    ness
    1.01
    ened
    1.00
     voices
    0.98
    ening
    0.95
     noises
    0.94
     fry
    0.88
    Activations Density 0.027%

    No Known Activations