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. 10993
    Prev
    Next
    INDEX
    Explanations

    references to music records or albums

    oai_token-act-pair · gpt-3.5-turbo

    references to music records and their releases

    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
     Liang
    -0.75
    Ĭ±
    -0.73
    laus
    -0.72
    hin
    -0.69
     Dent
    -0.68
    cius
    -0.68
     hypert
    -0.64
    aukee
    -0.64
     htt
    -0.63
     Leth
    -0.63
    POSITIVE LOGITS
     albums
    0.93
    stores
    0.89
     labels
    0.84
    isphere
    0.84
     cassette
    0.83
    orders
    0.83
    company
    0.83
     producer
    0.77
     label
    0.76
     Label
    0.76
    Activations Density 0.034%

    No Known Activations