© 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. 7-RES-JB
    11. 242
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "We are" followed by an adjective or verb

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the phrase "we are."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rouse
    -0.74
    odor
    -0.70
    othal
    -0.64
    weed
    -0.63
     mater
    -0.63
     entails
    -0.63
     emerges
    -0.63
    ossom
    -0.63
    osate
    -0.62
    Shape
    -0.61
    POSITIVE LOGITS
     glad
    1.03
     thankful
    1.03
     aware
    1.00
     fortunate
    1.00
     proud
    0.97
     hereby
    0.96
     grateful
    0.96
     gonna
    0.91
     ourselves
    0.89
     obliged
    0.89
    Activations Density 0.160%

    No Known Activations