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. 1-RES-JB
    6. 19783
    Prev
    Next
    INDEX
    Explanations

    words related to sound or noise

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "loud."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     coli
    -0.74
    photos
    -0.74
    clipse
    -0.69
     Photos
    -0.67
    CBS
    -0.64
     Kund
    -0.64
    CG
    -0.64
    issors
    -0.63
    ribe
    -0.63
    GRE
    -0.62
    POSITIVE LOGITS
     loud
    1.25
     louder
    1.25
    mouth
    1.11
    eners
    1.07
    ened
    0.98
     noises
    0.96
    ness
    0.91
     speaker
    0.91
     loudly
    0.87
    etooth
    0.85
    Activations Density 0.007%

    No Known Activations