© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 23753
    Prev
    Next
    INDEX
    Explanations

    time-related phrases indicating the duration or age of events or things

    oai_token-act-pair · gpt-3.5-turbo

    references to the passage of time and its historical significance

    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
    Tuesday
    -0.67
    emouth
    -0.67
    PAC
    -0.62
    Wednesday
    -0.62
    Adds
    -0.61
     PAN
    -0.61
    Friday
    -0.61
     POLITICO
    -0.60
     Oversight
    -0.60
     Collider
    -0.60
    POSITIVE LOGITS
     millennia
    1.94
     centuries
    1.90
     millennium
    1.80
     century
    1.63
     generations
    1.57
     decades
    1.52
    century
    1.43
     thousand
    1.32
     hundred
    1.32
     fifty
    1.20
    Activations Density 0.189%

    No Known Activations