© 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. 20480
    Prev
    Next
    INDEX
    Explanations

    phrases related to high levels or rates of something

    oai_token-act-pair · gpt-3.5-turbo

    references to high levels or degrees of various attributes or conditions

    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
    ription
    -0.79
    tnc
    -0.72
    herer
    -0.71
    oute
    -0.67
    itars
    -0.67
    ource
    -0.64
    ocene
    -0.63
    izon
    -0.63
    irit
    -0.62
    vier
    -0.62
    POSITIVE LOGITS
     percentage
    1.21
     degree
    1.15
     levels
    1.07
     percentages
    1.06
     probability
    1.05
     incidence
    1.04
     proportion
    1.04
     rate
    1.03
     rates
    1.03
     level
    1.02
    Activations Density 0.070%

    No Known Activations