© 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 EvalsExportsAPI 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. 10898
    Prev
    Next
    INDEX
    Explanations

    phrases related to missing something or someone

    oai_token-act-pair · gpt-3.5-turbo

    the word "miss" and its variations, indicating themes of loss or omission

    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
     Jinping
    -0.67
    loo
    -0.67
     inferred
    -0.62
    optional
    -0.61
    -0.61
     Continued
    -0.59
    rim
    -0.57
    gars
    -0.57
    DX
    -0.56
     independently
    -0.56
    POSITIVE LOGITS
    pelled
    1.30
    hap
    1.24
    pell
    1.08
    poke
    1.08
    pelling
    1.06
    peak
    1.03
     deadlines
    0.93
    ouri
    0.89
    auga
    0.84
    cules
    0.80
    Activations Density 0.031%

    No Known Activations