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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 4003
    Prev
    Next
    INDEX
    Explanations

    mention of songs or song-related terms in text

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the word "song."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alsh
    -0.78
    orate
    -0.73
    etheless
    -0.69
     Kear
    -0.69
     Goods
    -0.68
    cffff
    -0.68
    elsius
    -0.67
    rontal
    -0.65
     unchecked
    -0.65
     Inqu
    -0.65
    POSITIVE LOGITS
    writer
    1.45
    writers
    1.38
     lyrics
    1.32
    writing
    1.31
    stress
    1.20
     lyric
    1.12
    bird
    1.10
    song
    1.07
     song
    1.06
    birds
    0.99
    Activations Density 0.018%

    No Known Activations