© 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. 3490
    Prev
    Next
    INDEX
    Explanations

    the word "sing" or variations of it in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sing" in various contexts

    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
    pora
    -0.69
    imaru
    -0.67
    othal
    -0.66
    EStreamFrame
    -0.66
    committee
    -0.65
    ENTION
    -0.64
    hift
    -0.63
     Inquiry
    -0.63
     Chiefs
    -0.62
     Hussain
    -0.62
    POSITIVE LOGITS
     sing
    1.13
    leness
    1.06
     sung
    1.05
    lest
    0.97
     Sing
    0.95
    sing
    0.88
    stress
    0.85
     aloud
    0.85
     lyrics
    0.84
    song
    0.82
    Activations Density 0.006%

    No Known Activations