© 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. 8-RES-JB
    11. 24328
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names related to various topics or individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and titles related to media and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anwhile
    -0.71
    mble
    -0.69
    hement
    -0.65
    */(
    -0.63
    enegger
    -0.63
     loader
    -0.63
    assetsadobe
    -0.61
    cffffcc
    -0.61
    inates
    -0.58
    ¶ħ
    -0.57
    POSITIVE LOGITS
    Coin
    0.64
    Fest
    0.61
    coin
    0.58
    Wiki
    0.56
    Camp
    0.56
    opia
    0.52
     Dynasty
    0.52
    Ben
    0.51
    gress
    0.51
    World
    0.50
    Activations Density 0.879%

    No Known Activations