© 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. 9884
    Prev
    Next
    INDEX
    Explanations

    specific time references

    oai_token-act-pair · gpt-3.5-turbo

    decimal points in numerical values, particularly those related to time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     spo
    -0.72
    Ĥª
    -0.71
    ·
    -0.69
     behav
    -0.68
    isations
    -0.63
     jealous
    -0.62
    URI
    -0.62
    izoph
    -0.61
    abulary
    -0.61
    ı
    -0.60
    POSITIVE LOGITS
     EDT
    1.33
     ET
    1.28
     EST
    1.20
     CST
    1.19
     PDT
    1.18
     PST
    1.12
     CET
    1.08
     PT
    1.05
     Fridays
    0.95
     Thurs
    0.92
    Activations Density 0.038%

    No Known Activations