© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 17577
    Prev
    Next
    INDEX
    Explanations

    future predictions or speculations by examining phrases that indicate extrapolation or anticipation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to fate and the passage of 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
    selage
    -0.80
    artney
    -0.75
    outheastern
    -0.73
     sidx
    -0.70
    inia
    -0.69
    unal
    -0.69
    ocial
    -0.69
    ebted
    -0.68
    iatric
    -0.68
    ospons
    -0.67
    POSITIVE LOGITS
     dictates
    0.99
     dictate
    0.95
     abound
    0.83
     trump
    0.82
     intervened
    0.76
     Kinnikuman
    0.74
     trick
    0.71
     tricks
    0.71
     prevailed
    0.71
     favor
    0.69
    Activations Density 0.442%

    No Known Activations