© 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. 981
    Prev
    Next
    INDEX
    Explanations

    references to specific sizes or measurements

    oai_token-act-pair · gpt-3.5-turbo

    numbers and measurements typically related to film formats and dimensions

    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
    atically
    -0.74
     Machina
    -0.72
    atis
    -0.69
     Kik
    -0.67
     Gupta
    -0.66
     Shutterstock
    -0.65
     prov
    -0.65
    atem
    -0.65
    akov
    -0.64
    pora
    -0.64
    POSITIVE LOGITS
    dfx
    0.91
    %-
    0.89
    DD
    0.82
    ÃĹ
    0.80
    th
    0.73
     watt
    0.72
    XX
    0.72
     dimensional
    0.70
    x
    0.70
    Ball
    0.70
    Activations Density 0.206%

    No Known Activations