© 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. 2-RES-JB
    11. 23405
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressions of joy or support, specifically the word "cheer" and its variations

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to cheerfulness and celebration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 2 - joy

    No Comments

    Negative Logits
     sequest
    -0.73
    uncture
    -0.71
    amation
    -0.67
    entin
    -0.66
    orgetown
    -0.66
    arin
    -0.65
    enture
    -0.64
     scissors
    -0.64
    uture
    -0.63
     Danger
    -0.62
    POSITIVE LOGITS
     cheer
    1.20
    leader
    1.16
     cheering
    1.10
     cheered
    1.09
    leading
    1.04
     cheers
    1.03
    fulness
    0.97
    leaders
    0.95
    lead
    0.85
    hovah
    0.82
    Activations Density 0.007%

    No Known Activations