© 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. 2950
    Prev
    Next
    INDEX
    Explanations

    terms related to communication and collaboration among team members

    oai_token-act-pair · gpt-3.5-turbo

    instances of communication and collaboration among team members

    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
     revenge
    -0.65
    ãĥ©ãĥ³
    -0.64
     Tsukuyomi
    -0.61
     Wrong
    -0.61
    acha
    -0.60
    INTON
    -0.60
     displacement
    -0.59
    士
    -0.59
    peat
    -0.59
     belongs
    -0.59
    POSITIVE LOGITS
     whenever
    1.06
     throughout
    1.03
     briefings
    0.99
     lia
    0.91
     advising
    0.91
     communicating
    0.91
     during
    0.90
     regarding
    0.90
     informing
    0.89
     explaining
    0.88
    Activations Density 0.431%

    No Known Activations