© 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. 10156
    Prev
    Next
    INDEX
    Explanations

    instances of communication actions

    oai_token-act-pair · gpt-3.5-turbo

    references to sending messages or communications

    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
    iqueness
    -0.70
     similarities
    -0.69
    yrs
    -0.67
    shed
    -0.67
    irk
    -0.67
    livious
    -0.66
    anse
    -0.66
    yrights
    -0.65
     pores
    -0.65
     facets
    -0.65
    POSITIVE LOGITS
     message
    1.15
     condolences
    1.05
     invitations
    1.02
     packing
    1.01
     mail
    0.99
     congrat
    0.97
     messenger
    0.97
     messages
    0.95
     Message
    0.95
     fax
    0.95
    Activations Density 0.162%

    No Known Activations