© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4994
    Prev
    Next
    INDEX
    Explanations

    specific numbers identified as IDs, codes, or part of lists

    oai_token-act-pair · gpt-3.5-turbo

    numerical references or statistics related to categories or classifications

    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
    fman
    -0.67
    -|
    -0.64
    jo
    -0.64
    jew
    -0.60
     branding
    -0.60
    irtual
    -0.60
    tarian
    -0.60
    ucker
    -0.59
    ndra
    -0.58
     bund
    -0.58
    POSITIVE LOGITS
     112
    2.46
     114
    2.44
     115
    2.41
     113
    2.40
     109
    2.36
     111
    2.32
     116
    2.31
     110
    2.30
     107
    2.29
     108
    2.27
    Activations Density 0.027%

    No Known Activations