© 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. 1725
    Prev
    Next
    INDEX
    Explanations

    phrases related to spreading information or messages within a community

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases emphasizing the act of spreading information or messages

    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
    */(
    -1.01
     Dealer
    -0.70
    ocene
    -0.70
    tarians
    -0.69
    herical
    -0.67
    hov
    -0.67
    ivot
    -0.64
    collection
    -0.63
    ilateral
    -0.63
    artments
    -0.63
    POSITIVE LOGITS
     gospel
    1.26
     message
    1.13
     word
    1.12
     misinformation
    1.12
     rumor
    1.06
     leaflets
    1.02
     disinformation
    1.01
     knowledge
    1.01
     rumors
    0.98
     awareness
    0.98
    Activations Density 0.141%

    No Known Activations