© 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. 8-RES-JB
    11. 17780
    Prev
    Next
    INDEX
    Explanations

    instructions referring to specific reasons and details for incompatibility with a certain item or system

    oai_token-act-pair · gpt-3.5-turbo

    references to instructions and guidelines for usage

    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
    âĹ¼
    -0.67
    mouth
    -0.65
    opped
    -0.64
    odied
    -0.64
    inals
    -0.63
     imperson
    -0.63
    rained
    -0.62
     awoke
    -0.61
    ãĤ¼ãĤ¦ãĤ¹
    -0.61
     simul
    -0.61
    POSITIVE LOGITS
     FAQ
    1.08
     datas
    0.97
     wiki
    0.96
    FAQ
    0.93
     docs
    0.89
     documentation
    0.88
    autions
    0.88
     section
    0.88
     Gloss
    0.85
     appendix
    0.84
    Activations Density 0.282%

    No Known Activations