© 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. 10-RES-JB
    11. 10470
    Prev
    Next
    INDEX
    Explanations

    statements of hope or optimism

    oai_token-act-pair · gpt-3.5-turbo

    expressions of hope and expectation

    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
    ãĤ¨ãĥ«
    -0.77
    emp
    -0.74
    arse
    -0.73
    emate
    -0.73
    raq
    -0.72
    oba
    -0.71
    aches
    -0.70
    WAYS
    -0.70
    ãĤĵ
    -0.69
    ynes
    -0.69
    POSITIVE LOGITS
     someday
    1.50
     future
    0.98
     whoever
    0.98
     eventually
    0.89
     tomorrow
    0.88
     sooner
    0.83
     someone
    0.82
     whichever
    0.82
     unforeseen
    0.81
    eday
    0.79
    Activations Density 0.150%

    No Known Activations