© 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. 12-RES-JB
    11. 4232
    Prev
    Next
    INDEX
    Explanations

    proper names, particularly related to entertainment industry figures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    occurrences of the name "Jessica" and related characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    bably
    -0.71
    requ
    -0.68
    ptions
    -0.68
    ounded
    -0.67
    ãĥĭ
    -0.64
    qual
    -0.63
    assing
    -0.63
    brid
    -0.62
    brance
    -0.62
    é¾
    -0.60
    POSITIVE LOGITS
     Valent
    0.99
     Nig
    0.89
     Rabbit
    0.85
     Lange
    0.82
     Leeds
    0.79
    ellen
    0.77
    ournals
    0.68
     Barth
    0.65
    apan
    0.65
     Slate
    0.64
    Activations Density 0.105%

    No Known Activations