© 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. 9872
    Prev
    Next
    INDEX
    Explanations

    words related to motivation, inspiration, empowerment, encouragement, support, and shaping a positive future

    oai_token-act-pair · gpt-3.5-turbo

    expressions of hope and encouragement toward personal or community empowerment

    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
    atism
    -0.73
     largeDownload
    -0.66
    Newsletter
    -0.66
    £ı
    -0.65
    lig
    -0.65
    paio
    -0.63
     brut
    -0.62
    tics
    -0.62
    tarian
    -0.61
    ilitary
    -0.60
    POSITIVE LOGITS
     future
    1.16
     someday
    1.05
     brighter
    0.95
     hopefully
    0.94
     generations
    0.88
     others
    0.86
     further
    0.84
     tomorrow
    0.84
     hereafter
    0.83
     eventual
    0.80
    Activations Density 0.719%

    No Known Activations