© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 5419
    Prev
    Next
    INDEX
    Explanations

    the pronoun "we" used in research or academic contexts

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the pronoun "we" as a marker for collective actions or statements

    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
     Crest
    -0.80
    Posts
    -0.78
     srfAttach
    -0.72
    Champ
    -0.69
    Offline
    -0.65
     Alphabet
    -0.64
    Appearances
    -0.64
    wives
    -0.64
     bragging
    -0.61
    VERTISEMENT
    -0.61
    POSITIVE LOGITS
     hypothesized
    1.22
     conclude
    1.13
     hypothes
    1.10
     examined
    1.08
     propose
    1.07
     demonstrate
    1.06
     observe
    1.06
     observed
    1.03
     assessed
    1.01
     undertook
    1.01
    Activations Density 0.077%

    No Known Activations