© 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. 10-RES-JB
    11. 2918
    Prev
    Next
    INDEX
    Explanations

    contractions of "we are"

    oai_token-act-pair · gpt-3.5-turbo

    contractions, particularly "we're" and "I'm," indicating a focus on personal and collective statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ESE
    -0.75
    andise
    -0.68
    iox
    -0.67
    odder
    -0.67
    TAIN
    -0.67
    \/
    -0.65
    DS
    -0.64
    ren
    -0.63
    æĪ¦
    -0.60
    Scroll
    -0.60
    POSITIVE LOGITS
     gonna
    1.41
     gotta
    1.13
     sorry
    1.05
     guessing
    0.98
     going
    0.97
     not
    0.97
     hoping
    0.95
     glad
    0.95
     afraid
    0.93
     supposed
    0.91
    Activations Density 0.076%

    No Known Activations