Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 16653
    Prev
    Next
    INDEX
    Explanations

    references to locations and events related to news articles

    oai_token-act-pair · gpt-3.5-turbo

    sentences that indicate closures or interruptions in societal functions

    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
     persu
    -0.88
     tempt
    -0.79
     induct
    -0.76
     usur
    -0.75
     exoner
    -0.75
     adopting
    -0.74
     persuasion
    -0.74
     plaus
    -0.74
     tailored
    -0.73
     willingly
    -0.73
    POSITIVE LOGITS
    Hundreds
    1.34
    Emergency
    1.34
    Authorities
    1.29
    Thousands
    1.23
     Hundreds
    1.22
    Officials
    1.18
     Dozens
    1.16
    Residents
    1.16
     Thousands
    1.14
     Emergency
    1.14
    Activations Density 0.424%

    No Known Activations