© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1894
    Prev
    Next
    INDEX
    Explanations

    mentions of cheering or expressions of joy

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "cheer" and related forms

    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
    ngth
    -0.76
    arin
    -0.72
    enture
    -0.68
    ahime
    -0.67
    uture
    -0.67
    orgetown
    -0.65
     sequest
    -0.64
     fung
    -0.62
     wedge
    -0.62
    ighth
    -0.61
    POSITIVE LOGITS
    leader
    1.24
    leading
    1.19
     cheer
    1.17
    leaders
    1.11
    fulness
    1.04
     cheering
    1.01
     cheered
    0.99
    lead
    0.95
     cheers
    0.87
    fully
    0.86
    Activations Density 0.010%

    No Known Activations