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. 7-RES-JB
    6. 10725
    Prev
    Next
    INDEX
    Explanations

    content related to website interaction, social media communication, and customer engagement

    oai_token-act-pair · gpt-3.5-turbo

    engagement metrics and interactions related to social media content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DERR
    -0.65
    »Ĵ
    -0.65
    ĸļ
    -0.63
    erness
    -0.63
    ©¶æ¥µ
    -0.62
     Oaks
    -0.62
    MRI
    -0.61
     Ramsey
    -0.60
    ometry
    -0.59
     Morg
    -0.59
    POSITIVE LOGITS
     guiActive
    0.82
    iframe
    0.72
     bookmark
    0.68
    minded
    0.65
    yip
    0.65
    podcast
    0.64
     FACE
    0.63
    Subscribe
    0.63
     Subscribe
    0.63
     Advertisement
    0.62
    Activations Density 0.078%

    No Known Activations