© 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. 20551
    Prev
    Next
    INDEX
    Explanations

    phrases related to uncertainty or lack of information

    oai_token-act-pair · gpt-3.5-turbo

    words related to likelihood and the presentation of information or arguments

    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
     glim
    -0.66
    loads
    -0.61
     Been
    -0.60
     goose
    -0.59
     Anyway
    -0.59
    Joined
    -0.56
    packed
    -0.55
     crispy
    -0.55
     laun
    -0.54
    Got
    -0.53
    POSITIVE LOGITS
     cannot
    1.59
     does
    1.48
     did
    1.46
     do
    1.42
    does
    1.27
    do
    1.22
    did
    1.21
     DOES
    1.19
     lacks
    1.13
     DO
    1.13
    Activations Density 0.831%

    No Known Activations