© 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. 1-RES-JB
    11. 7683
    Prev
    Next
    INDEX
    Explanations

    texts or contexts related to happiness

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to happiness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 1 - happiness

    No Comments

    Negative Logits
    $$$$
    -0.81
    DoS
    -0.75
    âĵĺ
    -0.72
    sites
    -0.71
    OLOGY
    -0.71
    Downloadha
    -0.71
    href
    -0.69
    BOOK
    -0.67
    Maps
    -0.67
    IDs
    -0.67
    POSITIVE LOGITS
     happy
    1.10
    happy
    0.86
     happily
    0.81
     satisfied
    0.79
     birthday
    0.76
     happiest
    0.76
     Happy
    0.75
     ecstatic
    0.75
     rejoice
    0.75
    joy
    0.74
    Activations Density 0.013%

    No Known Activations