© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 7160
    Prev
    Next
    INDEX
    Explanations

    specific items or solutions within a context, such as "finding the right specs" or "finding the Loch Ness monster"

    oai_token-act-pair · gpt-3.5-turbo

    references to discovering or locating something valuable or important

    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
    amon
    -0.73
    assisted
    -0.65
    cour
    -0.64
     Nanto
    -0.64
    athering
    -0.63
    aken
    -0.62
    upt
    -0.60
     cautioned
    -0.60
    CBS
    -0.59
    ithering
    -0.59
    POSITIVE LOGITS
     suitable
    1.08
     replacements
    0.90
     scapego
    0.89
     elusive
    0.88
     replacement
    0.86
    ById
    0.86
     effic
    0.84
     loopholes
    0.84
     nearest
    0.82
     ways
    0.80
    Activations Density 0.404%

    No Known Activations