© 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. 11-RES-JB
    11. 7592
    Prev
    Next
    INDEX
    Explanations

    religious or ceremonial phrases or expressions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'g' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ples
    -0.64
     Alley
    -0.63
     retrospect
    -0.62
     attendance
    -0.60
     HK
    -0.60
     refere
    -0.58
     Fug
    -0.57
     Bree
    -0.57
     HUN
    -0.57
     tracker
    -0.57
    POSITIVE LOGITS
    reet
    1.42
    raphics
    1.40
    ossip
    1.40
    raphic
    1.36
    athering
    1.35
    reetings
    1.34
    hetto
    1.29
    ospel
    1.24
    asp
    1.23
    reens
    1.23
    Activations Density 0.028%

    No Known Activations