© 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. 2-RES-JB
    11. 23864
    Prev
    Next
    INDEX
    Explanations

    the word "hopeful"

    oai_token-act-pair · gpt-3.5-turbo

    expressions of hope

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    leigh
    -0.88
    pper
    -0.83
    classified
    -0.76
    hire
    -0.75
    gar
    -0.75
    assault
    -0.73
    pmwiki
    -0.73
    asus
    -0.72
    pes
    -0.71
    avis
    -0.71
    POSITIVE LOGITS
     hopeful
    1.21
     optimism
    0.89
     optimistic
    0.87
     prospects
    0.81
    eful
    0.72
     Neh
    0.72
     dialogue
    0.71
     upbeat
    0.71
    ial
    0.70
     Prosper
    0.69
    Activations Density 0.008%

    No Known Activations