© 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. 24399
    Prev
    Next
    INDEX
    Explanations

    mentions of food related to lunch

    oai_token-act-pair · gpt-3.5-turbo

    mentions of meals, particularly lunch and its context

    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
    ignty
    -0.75
    SPONSORED
    -0.67
     CSI
    -0.66
    Constructed
    -0.66
     infertility
    -0.65
     persecution
    -0.65
     annexed
    -0.61
    fitting
    -0.61
    Filename
    -0.58
    66666666
    -0.58
    POSITIVE LOGITS
    time
    1.12
    bowl
    1.05
    wich
    0.97
    aturday
    0.96
    eteria
    0.96
    boxes
    0.92
    bag
    0.89
    worms
    0.89
    ablishment
    0.86
    iday
    0.85
    Activations Density 0.030%

    No Known Activations