© 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. 7-RES-JB
    11. 23751
    Prev
    Next
    INDEX
    Explanations

    phrases related to chanting

    oai_token-act-pair · gpt-3.5-turbo

    instances of collective vocal expressions or chants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    士
    -0.77
    neau
    -0.75
    amate
    -0.74
    carb
    -0.70
    uckland
    -0.67
    axter
    -0.66
    ulent
    -0.66
    iasis
    -0.66
    éĸ
    -0.66
    Admin
    -0.65
    POSITIVE LOGITS
     chanting
    1.27
     chants
    1.18
     chant
    1.16
     chanted
    1.15
     louder
    0.97
     slogans
    0.85
     loudly
    0.84
     aloud
    0.80
    hovah
    0.78
     cheering
    0.77
    Activations Density 0.036%

    No Known Activations