© 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. 11-RES-JB
    11. 20437
    Prev
    Next
    INDEX
    Explanations

    social media platform names specifically Facebook

    oai_token-act-pair · gpt-3.5-turbo

    references to Facebook

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bilt
    -0.74
    rals
    -0.73
    plane
    -0.71
    ACTED
    -0.68
    ppa
    -0.66
    tti
    -0.63
    akin
    -0.63
    rans
    -0.62
    gran
    -0.62
    stood
    -0.62
    POSITIVE LOGITS
     Twitter
    1.10
    Twitter
    0.92
     Pinterest
    0.85
     Comments
    0.85
     Tweet
    0.82
    Tumblr
    0.79
    twitter
    0.76
     Email
    0.76
     Likes
    0.76
    LinkedIn
    0.73
    Activations Density 0.040%

    No Known Activations