© 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. 3795
    Prev
    Next
    INDEX
    Explanations

    titles, names, or references to songs

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Song" 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
    orate
    -0.81
    rontal
    -0.80
     Kear
    -0.77
     Pradesh
    -0.69
    fitted
    -0.64
    etheless
    -0.63
    astical
    -0.62
    agons
    -0.62
     LAT
    -0.60
    remlin
    -0.59
    POSITIVE LOGITS
    Song
    1.45
     Song
    1.44
     Songs
    1.24
    song
    1.17
     lyrics
    1.15
    writer
    1.08
    writers
    1.04
    bird
    1.01
    writing
    0.99
     lyric
    0.98
    Activations Density 0.006%

    No Known Activations