© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 12-RES-JB
    6. 4318
    Prev
    Next
    INDEX
    Explanations

    names or proper nouns that are typically accompanied by initials or abbreviations

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

    words related to a specific name or letter

    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
    Artist
    -0.79
    arty
    -0.79
     contrace
    -0.76
    DragonMagazine
    -0.68
    reon
    -0.68
    asel
    -0.67
    IRC
    -0.66
    ãĥŃ
    -0.66
    Lua
    -0.65
    IE
    -0.64
    POSITIVE LOGITS
     p
    0.69
     c
    0.64
     th
    0.60
     Britain
    0.59
     ball
    0.57
     pel
    0.56
     s
    0.55
     belong
    0.55
     bit
    0.55
    enegger
    0.54
    Activations Density 0.183%

    No Known Activations