© 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. 10-RES-JB
    11. 14096
    Prev
    Next
    INDEX
    Explanations

    time-related phrases, specifically focusing on past events

    oai_token-act-pair · gpt-3.5-turbo

    references to past events indicated by time expressions

    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
    emo
    -0.62
    eq
    -0.60
    eers
    -0.60
    aspx
    -0.59
    hner
    -0.57
    rera
    -0.56
    nce
    -0.55
    ues
    -0.55
    THER
    -0.55
    eer
    -0.55
    POSITIVE LOGITS
    opausal
    0.84
     when
    0.72
    tical
    0.68
     today
    0.68
    orescence
    0.66
    é¾įåĸļ士
    0.65
     WHEN
    0.65
    ,
    0.65
    èª
    0.63
    agher
    0.63
    Activations Density 0.043%

    No Known Activations