© 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. 11094
    Prev
    Next
    INDEX
    Explanations

    names of individuals, likely researchers or authors

    oai_token-act-pair · gpt-3.5-turbo

    prominent names and titles associated with studies or expert opinions

    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
     bathrooms
    -0.58
     puppies
    -0.57
     selfies
    -0.54
     disrespect
    -0.53
     partying
    -0.52
     dracon
    -0.52
     voters
    -0.52
     worse
    -0.52
     machines
    -0.52
     Pastebin
    -0.52
    POSITIVE LOGITS
     Kaufman
    0.85
     Schro
    0.85
     Shapiro
    0.83
     Walsh
    0.82
     Roh
    0.80
     Sch
    0.80
     Feldman
    0.80
     Kaplan
    0.79
     Doyle
    0.79
     Vog
    0.79
    Activations Density 0.332%

    No Known Activations