© 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. 12724
    Prev
    Next
    INDEX
    Explanations

    time-related expressions such as days, weeks, and months

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods or frequencies of occurrence

    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
    otto
    -0.70
    resy
    -0.66
    arton
    -0.64
    UCT
    -0.64
    ociate
    -0.64
    ItemTracker
    -0.63
    anamo
    -0.62
    emort
    -0.62
    URES
    -0.62
    aleb
    -0.61
    POSITIVE LOGITS
     thereafter
    1.17
     throughout
    0.86
    night
    0.82
     until
    0.80
     except
    0.78
     since
    0.76
     during
    0.74
    til
    0.74
     imaginable
    0.73
     regardless
    0.73
    Activations Density 0.071%

    No Known Activations