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. 6-RES-JB
    6. 17307
    Prev
    Next
    INDEX
    Explanations

    specific measurements and dimensions in a document, such as lengths, heights, and screen sizes

    oai_token-act-pair · gpt-3.5-turbo

    measurements and dimensions

    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
     Vi
    -0.72
    vik
    -0.66
    atu
    -0.64
    FUL
    -0.64
    CVE
    -0.64
     behav
    -0.62
     Buckley
    -0.62
     Samar
    -0.61
     Portug
    -0.61
    arie
    -0.61
    POSITIVE LOGITS
    (-
    0.77
    hedral
    0.74
    abytes
    0.74
    cm
    0.73
     magnification
    0.72
    factor
    0.71
    -+
    0.71
    ÏĤ
    0.70
    fold
    0.69
    pixel
    0.69
    Activations Density 0.058%

    No Known Activations