© 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. 11-RES-JB
    11. 1414
    Prev
    Next
    INDEX
    Explanations

    actions related to communication and interaction within a team or community

    oai_token-act-pair · gpt-3.5-turbo

    activities related to collaboration and communication

    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
    azo
    -0.83
     extinct
    -0.73
    failed
    -0.72
    utterstock
    -0.71
    acho
    -0.70
    oldemort
    -0.70
     disadvantage
    -0.68
    Size
    -0.68
    angled
    -0.67
    Result
    -0.66
    POSITIVE LOGITS
     chats
    1.35
     lia
    1.22
     briefings
    1.16
     chatting
    1.12
     occasionally
    1.12
     chat
    1.10
     answering
    1.03
     advising
    1.02
     constantly
    1.01
     seminars
    1.01
    Activations Density 0.546%

    No Known Activations