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

    Neuronpedia

    Jacobian LensNEW
    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. 9949
    Prev
    Next
    INDEX
    Explanations

    mentions of the social media platform "Instagram."

    oai_token-act-pair · gpt-3.5-turbo

    references to social media platforms, particularly Instagram

    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
     promise
    -0.67
     strides
    -0.66
     guarantee
    -0.64
     BM
    -0.62
     tempered
    -0.62
     Cle
    -0.61
     rides
    -0.61
     professionals
    -0.61
     tires
    -0.61
     rebuild
    -0.61
    POSITIVE LOGITS
    agram
    4.99
    agonal
    1.53
    abase
    1.23
    agon
    1.20
    gram
    1.18
    othal
    1.06
    ograms
    1.03
    igraph
    1.01
    wikipedia
    0.99
    agraph
    0.98
    Activations Density 0.011%

    No Known Activations