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. 4-RES-JB
    6. 3083
    Prev
    Next
    INDEX
    Explanations

    information related to music releases, particularly singles and tracks

    oai_token-act-pair · gpt-3.5-turbo

    references to musical singles and their associated details

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

    No Comments

    Negative Logits
    EStreamFrame
    -0.72
    cephal
    -0.70
     Advantage
    -0.69
     wards
    -0.69
     Geographic
    -0.65
     cler
    -0.65
    xon
    -0.65
     ns
    -0.64
     Experts
    -0.64
     presiding
    -0.64
    POSITIVE LOGITS
     lyrics
    1.09
     album
    1.06
     albums
    1.06
    ixtape
    0.93
     lyric
    0.90
    Bey
    0.85
     songs
    0.84
     Songs
    0.83
    uesday
    0.83
    itled
    0.78
    Activations Density 0.090%

    No Known Activations