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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 17445
    Prev
    Next
    INDEX
    Explanations

    mentions of the pronoun "we"

    oai_token-act-pair · gpt-3.5-turbo

    the word "we" and its variations, indicating a focus on collective or group identity

    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
     firsthand
    -0.65
     Fortune
    -0.61
     srfAttach
    -0.60
     Seat
    -0.56
    Posts
    -0.55
     gratification
    -0.55
     undue
    -0.54
     quo
    -0.54
     Kush
    -0.53
     Cliff
    -0.52
    POSITIVE LOGITS
    asel
    1.47
    bsite
    1.41
    athered
    1.40
    lder
    1.32
    akening
    1.31
    eping
    1.30
    ldon
    1.28
    avers
    1.23
    aning
    1.21
    ibo
    1.21
    Activations Density 0.059%

    No Known Activations