© 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. 10-RES-JB
    11. 10519
    Prev
    Next
    INDEX
    Explanations

    appearances of the word "much" followed by a varying range of other words or characters

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating high anticipation or popularity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    instead
    -0.75
    ESE
    -0.75
    halla
    -0.72
    livious
    -0.71
     Suit
    -0.69
    afety
    -0.68
    elf
    -0.66
    eday
    -0.65
    ĺħ
    -0.65
     Provision
    -0.65
    POSITIVE LOGITS
     acclaimed
    1.39
     lauded
    1.27
     awaited
    1.23
     publicized
    1.22
     touted
    1.18
     controversial
    1.17
     anticipated
    1.12
     praised
    1.11
     criticized
    1.08
     beloved
    1.08
    Activations Density 0.126%

    No Known Activations