© 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. 10305
    Prev
    Next
    INDEX
    Explanations

    numbers with percentage signs

    oai_token-act-pair · gpt-3.5-turbo

    statistics and quantitative data related to rates and ratios

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    illions
    -0.71
    expensive
    -0.61
    æĸ¹
    -0.60
     purchase
    -0.60
     crowdfunding
    -0.59
    sale
    -0.59
     conting
    -0.58
    ques
    -0.58
     renamed
    -0.58
     datasets
    -0.57
    POSITIVE LOGITS
    %,
    1.20
    %.
    1.20
    %;
    1.12
    %-
    1.01
    %).
    0.87
     ±
    0.85
     msec
    0.83
    %
    0.83
     percent
    0.82
    %)
    0.82
    Activations Density 0.132%

    No Known Activations