Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 9887
    Prev
    Next
    INDEX
    Explanations

    references to the word "Song"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences 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 @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orate
    -0.84
    rontal
    -0.76
     Kear
    -0.74
    ardless
    -0.72
     Pradesh
    -0.68
    avez
    -0.67
    jamin
    -0.64
    lehem
    -0.64
    avis
    -0.63
    etheless
    -0.63
    POSITIVE LOGITS
    Song
    1.28
     Song
    1.17
    writer
    1.12
    writers
    1.10
    song
    1.07
     lyrics
    1.06
    bird
    1.05
     Songs
    1.04
    writing
    1.00
     lyric
    0.98
    Activations Density 0.007%

    No Known Activations