© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 12809
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a stance or position on a matter

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "we are" and variations thereof, indicating collective statements or affirmations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rouse
    -0.73
     mater
    -0.71
     meets
    -0.65
     bloc
    -0.65
    odor
    -0.65
    sed
    -0.64
    ousy
    -0.63
    othal
    -0.62
     emerges
    -0.62
    itters
    -0.61
    POSITIVE LOGITS
     ourselves
    0.98
     thankful
    0.94
     fortunate
    0.94
     glad
    0.93
     proud
    0.88
     hereby
    0.87
     grateful
    0.85
     gonna
    0.85
     aware
    0.85
     hoping
    0.84
    Activations Density 0.106%

    No Known Activations