© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 23169
    Prev
    Next
    INDEX
    Explanations

    phrases related to time periods, specifically centuries

    oai_token-act-pair · gpt-3.5-turbo

    references to different centuries, particularly the 19th and 20th centuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intern
    -0.65
     pro
    -0.64
     multipl
    -0.63
     internally
    -0.62
     preparation
    -0.62
     SK
    -0.61
     eg
    -0.60
     Nug
    -0.60
     spam
    -0.60
     green
    -0.59
    POSITIVE LOGITS
    century
    4.11
     century
    2.14
     Century
    1.69
     centuries
    1.37
     millennium
    1.35
     millennia
    1.28
    dozen
    1.19
    Cent
    1.14
     decade
    1.07
    modern
    1.06
    Activations Density 0.016%

    No Known Activations