© 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 EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 11266
    Prev
    Next
    INDEX
    Explanations

    social media features, like buttons and loading indicators

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "like" in varying contexts, particularly in relation to social media interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.64
    eval
    -0.63
    vernment
    -0.62
    deal
    -0.61
    Ö¼
    -0.61
     intermedi
    -0.61
    Marginal
    -0.61
    =-=-
    -0.59
    Definition
    -0.58
    Ãį
    -0.56
    POSITIVE LOGITS
    lihood
    1.36
    minded
    0.82
    liness
    0.70
     Us
    0.69
    liest
    0.68
    lier
    0.66
     minded
    0.65
     Submit
    0.65
    hovah
    0.62
    facebook
    0.61
    Activations Density 0.019%

    No Known Activations