© 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. 3-RES-JB
    11. 15536
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences ending with the word "added."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "added" in the context of statements or claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ardless
    -0.73
     Twin
    -0.71
    FL
    -0.67
    view
    -0.67
     Bos
    -0.66
    cies
    -0.63
     Bran
    -0.62
    bin
    -0.61
    fell
    -0.61
    Bir
    -0.60
    POSITIVE LOGITS
    ictions
    0.96
    itionally
    0.88
    itious
    0.86
    itions
    0.85
    itional
    0.84
    endum
    0.84
    itivity
    0.83
    missions
    0.81
     insult
    0.81
    eele
    0.80
    Activations Density 0.039%

    No Known Activations