© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14208
    Prev
    Next
    INDEX
    Explanations

    words related to technology and innovation

    oai_token-act-pair · gpt-3.5-turbo

    references to media production or changes in creative projects

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    jee
    -0.80
    quickShipAvailable
    -0.75
     negligence
    -0.66
     extremes
    -0.63
     bother
    -0.63
     nerves
    -0.60
     aback
    -0.60
     glare
    -0.60
    unts
    -0.60
     irritated
    -0.58
    POSITIVE LOGITS
     incorporating
    0.85
     Called
    0.83
     consisting
    0.79
     embod
    0.76
     modeled
    0.76
     dubbed
    0.75
     combining
    0.72
     resembling
    0.71
     christ
    0.71
    named
    0.71
    Activations Density 0.614%

    No Known Activations