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. 8-RES-JB
    6. 7436
    Prev
    Next
    INDEX
    Explanations

    categories or sections of a webpage

    oai_token-act-pair · gpt-3.5-turbo

    instances of numeric values and timestamps

    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
    ©¶æ
    -0.75
     Painter
    -0.74
     spitting
    -0.73
     sculpt
    -0.73
     manif
    -0.73
     lifes
    -0.72
     unaccount
    -0.72
     grop
    -0.71
     clin
    -0.71
     inspecting
    -0.71
    POSITIVE LOGITS
    Related
    1.38
    Advertisements
    1.37
    Topics
    1.34
    Share
    1.32
    Subscribe
    1.29
    Download
    1.28
    Contribut
    1.26
    Email
    1.26
    Comments
    1.26
    Tags
    1.25
    Activations Density 0.176%

    No Known Activations