© 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. 0-RES-JB
    11. 13323
    Prev
    Next
    INDEX
    Explanations

    numbers in the vicinity of 85

    oai_token-act-pair · gpt-3.5-turbo

    references to the number 85

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Embedding Space Digit Features

    No Comments

    Negative Logits
    wcsstore
    -0.85
    ples
    -0.76
    ple
    -0.73
     Clover
    -0.72
    gery
    -0.68
     RELE
    -0.67
     Josh
    -0.67
     Hulu
    -0.67
     Lep
    -0.65
     Jinn
    -0.64
    POSITIVE LOGITS
     85
    2.09
     84
    2.00
    85
    1.96
     86
    1.95
     83
    1.90
     82
    1.83
    84
    1.80
     81
    1.71
     87
    1.69
    83
    1.67
    Activations Density 0.059%

    No Known Activations