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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 8801
    Prev
    Next
    INDEX
    Explanations

    musical tracks or singles in written content

    oai_token-act-pair · gpt-3.5-turbo

    terms related to music tracks and singles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Marriott
    -0.74
    raham
    -0.69
     presiding
    -0.67
     Hockey
    -0.67
    aples
    -0.66
     Dent
    -0.66
    phthal
    -0.65
    cephal
    -0.65
    xon
    -0.64
     Geographic
    -0.64
    POSITIVE LOGITS
     lyrics
    1.15
     albums
    1.04
     album
    1.04
     lyric
    1.02
     songs
    0.95
    ixtape
    0.93
     vocals
    0.86
     Songs
    0.84
     remix
    0.83
    itled
    0.81
    Activations Density 0.102%

    No Known Activations