© 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. 10-RES-JB
    11. 8218
    Prev
    Next
    INDEX
    Explanations

    social media platform names and handles

    oai_token-act-pair · gpt-3.5-turbo

    connections to social media platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emen
    -0.72
    duration
    -0.64
    activity
    -0.64
     regulation
    -0.63
    cube
    -0.61
    tis
    -0.60
    holding
    -0.59
    ãĥ¯ãĥ³
    -0.58
    Sov
    -0.58
    imposed
    -0.58
    POSITIVE LOGITS
     facebook
    1.17
     Facebook
    1.13
     subscribe
    1.13
    facebook
    1.13
     Twitter
    1.06
     twitter
    1.04
     Instagram
    0.97
     Follow
    0.94
     Subscribe
    0.93
    Twitter
    0.92
    Activations Density 0.072%

    No Known Activations