© 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. 6-RES-JB
    11. 9354
    Prev
    Next
    INDEX
    Explanations

    quantitative values such as numbers or percentages

    oai_token-act-pair · gpt-3.5-turbo

    references to groups or categories of people or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bombs
    -0.67
    leep
    -0.65
     tun
    -0.61
     assum
    -0.60
    lest
    -0.59
     researching
    -0.59
     forget
    -0.58
    uning
    -0.57
     digging
    -0.57
     undet
    -0.57
    POSITIVE LOGITS
     pinnacle
    0.76
    ICAN
    0.70
    OPLE
    0.69
    hematic
    0.69
     XY
    0.68
     constituents
    0.68
     culmination
    0.67
     entirety
    0.66
    opian
    0.65
    wark
    0.64
    Activations Density 0.151%

    No Known Activations