© 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. 1-RES-JB
    11. 3957
    Prev
    Next
    INDEX
    Explanations

    references to the act of singing

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "singing."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PF
    -0.82
    ivot
    -0.72
    EStreamFrame
    -0.68
    RT
    -0.68
    quickShipAvailable
    -0.68
    aunder
    -0.66
    imaru
    -0.65
    jamin
    -0.64
    remlin
    -0.64
    EEK
    -0.64
    POSITIVE LOGITS
     sung
    1.39
     sang
    1.18
     singing
    1.18
     lyrics
    1.16
     singers
    1.15
     melodies
    1.08
     vocals
    1.07
     song
    1.07
     melody
    1.06
     songs
    1.05
    Activations Density 0.008%

    No Known Activations