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. 3528
    Prev
    Next
    INDEX
    Explanations

    social media platform names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of social media platforms, especially Twitter

    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
    sth
    -0.93
    sole
    -0.75
    ĪĴ
    -0.75
    onics
    -0.70
    mble
    -0.65
    rien
    -0.64
    clud
    -0.64
    kay
    -0.64
    -,
    -0.63
     rapp
    -0.62
    POSITIVE LOGITS
     Pinterest
    1.05
     Whats
    0.89
     LinkedIn
    0.77
    Pinterest
    0.71
     Patreon
    0.69
    Tumblr
    0.68
     ESA
    0.67
    LinkedIn
    0.67
     Tumblr
    0.66
     Google
    0.65
    Activations Density 0.024%

    No Known Activations