© 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. 3-RES-JB
    11. 15086
    Prev
    Next
    INDEX
    Explanations

    positive attitudes or hopeful outlooks, especially regarding future outcomes, policies, or events

    oai_token-act-pair · gpt-3.5-turbo

    expressions of optimism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avis
    -0.84
    hid
    -0.82
    hire
    -0.80
    drivers
    -0.79
    sites
    -0.78
    artifacts
    -0.76
    DoS
    -0.74
    installed
    -0.72
    deep
    -0.70
    ĸļ
    -0.70
    POSITIVE LOGITS
     optimism
    1.17
     optimistic
    1.17
    essim
    1.06
     upbeat
    1.01
     pessim
    0.92
     outlook
    0.91
     hopeful
    0.85
     pessimistic
    0.83
     atmosp
    0.81
     hope
    0.79
    Activations Density 0.018%

    No Known Activations