© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 1702
    Prev
    Next
    INDEX
    Explanations

    social media platform names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the social media platform Pinterest

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     blood
    -0.71
    blood
    -0.67
    Blood
    -0.66
     release
    -0.64
     recomp
    -0.63
     Blood
    -0.62
     acc
    -0.62
     caliber
    -0.59
     releases
    -0.59
    Ke
    -0.59
    POSITIVE LOGITS
     Pinterest
    4.22
    Pinterest
    2.27
     Tumblr
    1.66
     Flickr
    1.57
     LinkedIn
    1.57
     Etsy
    1.56
     Instagram
    1.55
     Yelp
    1.51
     Snapchat
    1.39
     Tinder
    1.33
    Activations Density 0.015%

    No Known Activations