© 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. 8-RES-JB
    11. 20345
    Prev
    Next
    INDEX
    Explanations

    references to time periods, specifically the phrases "past two" and "three years."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases related to time frames, specifically mentioning periods of two or three years

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    roid
    -0.67
    angan
    -0.64
    bos
    -0.61
    isky
    -0.61
    racuse
    -0.61
     Scully
    -0.60
     Selection
    -0.60
    trak
    -0.59
    RAG
    -0.59
     Rated
    -0.58
    POSITIVE LOGITS
     weeks
    1.12
     years
    1.10
     months
    1.10
     decades
    1.07
     generations
    1.01
     installments
    0.98
     seasons
    0.96
     millennia
    0.91
     days
    0.90
     centuries
    0.88
    Activations Density 0.053%

    No Known Activations