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

    Neuronpedia

    APICircuit 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. 8-RES-JB
    6. 16535
    Prev
    Next
    INDEX
    Explanations

    mentions of songs or song-related words

    oai_token-act-pair · gpt-3.5-turbo

    references to music and songs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Inqu
    -0.69
    ategory
    -0.68
    amily
    -0.66
    aples
    -0.66
    agons
    -0.65
     srfAttach
    -0.64
    achev
    -0.64
    iencies
    -0.61
    alsh
    -0.61
     Dhabi
    -0.60
    POSITIVE LOGITS
    writer
    1.58
    writers
    1.55
    stress
    1.52
    writing
    1.50
     lyrics
    1.46
    bird
    1.45
     lyric
    1.31
    birds
    1.28
     sung
    1.06
     songs
    1.05
    Activations Density 0.039%

    No Known Activations