© 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. 4-RES-JB
    11. 9569
    Prev
    Next
    INDEX
    Explanations

    words related to happiness and celebration

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Happy."

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

    No Comments

    Negative Logits
    arin
    -0.83
    IDER
    -0.82
    urally
    -0.79
    issues
    -0.74
    resent
    -0.74
    ently
    -0.74
    ents
    -0.73
    entin
    -0.72
    ij
    -0.72
    ifice
    -0.72
    POSITIVE LOGITS
     Happy
    0.96
     Birthday
    0.90
    ness
    0.84
    joy
    0.84
    Happy
    0.82
     birthday
    0.79
     Meal
    0.75
     happy
    0.73
    croft
    0.72
     Joy
    0.72
    Activations Density 0.013%

    No Known Activations