© 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. 9-RES-JB
    11. 24046
    Prev
    Next
    INDEX
    Explanations

    words related to technology, including specific terms like "rip", "ster", "genius", "network", "data frame", and "dragon"

    oai_token-act-pair · gpt-3.5-turbo

    words related to specific animals or food items

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Instr
    -0.83
     Ninth
    -0.77
     Seym
    -0.75
     Mayo
    -0.74
     Chatt
    -0.69
     Kik
    -0.69
     Fundamental
    -0.67
     Gong
    -0.66
     Kop
    -0.66
     Calder
    -0.66
    POSITIVE LOGITS
    _
    1.25
    @
    1.17
    ":{"
    1.06
    oft
    1.04
    _-_
    0.96
    basketball
    0.95
    clinton
    0.94
    podcast
    0.92
    circle
    0.92
    united
    0.89
    Activations Density 0.333%

    No Known Activations