© 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. 10739
    Prev
    Next
    INDEX
    Explanations

    expressions of joy and satisfaction

    oai_token-act-pair · gpt-3.5-turbo

    expressions of joy and pleasure

    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
    •layer 3 - joy

    No Comments

    Negative Logits
    enhagen
    -0.83
    ©¶æ
    -0.82
     mater
    -0.72
    prison
    -0.70
    eworld
    -0.68
     restraining
    -0.68
    road
    -0.68
    ioxide
    -0.67
    vernment
    -0.67
    xia
    -0.66
    POSITIVE LOGITS
    fully
    0.97
     delight
    0.91
    joy
    0.91
    ILY
    0.90
     delighted
    0.87
    iously
    0.76
    ingly
    0.75
    ously
    0.72
    lance
    0.72
     aston
    0.72
    Activations Density 0.012%

    No Known Activations