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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8-RES-JB
    6. 5790
    Prev
    Next
    INDEX
    Explanations

    phrases related to sheet music

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sheet" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Advocate
    -0.76
    essee
    -0.72
    Interstitial
    -0.71
    cius
    -0.68
    Pacific
    -0.67
     Valley
    -0.67
    ilee
    -0.66
    nings
    -0.66
    ourke
    -0.65
    £ı
    -0.64
    POSITIVE LOGITS
    sheet
    1.36
    sheets
    1.20
     sheets
    0.98
     sheet
    0.95
    sonian
    0.83
    paper
    0.81
    metal
    0.80
     thickness
    0.75
    meal
    0.75
    mination
    0.73
    Activations Density 0.034%

    No Known Activations