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. 4-RES-JB
    6. 23424
    Prev
    Next
    INDEX
    Explanations

    terms related to sound or sound quality

    oai_token-act-pair · gpt-3.5-turbo

    references to sound quality and its characteristics

    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
    apsed
    -0.78
     Mandela
    -0.77
     Lann
    -0.75
    olkien
    -0.75
     Ago
    -0.68
    ottesville
    -0.67
    udeau
    -0.67
    zona
    -0.65
    aples
    -0.64
     Osw
    -0.62
    POSITIVE LOGITS
    tracks
    1.21
    proof
    0.98
    bite
    0.96
    lessly
    0.93
    sound
    0.91
    checks
    0.87
     amplification
    0.80
     vibrations
    0.79
    bytes
    0.79
    board
    0.78
    Activations Density 0.015%

    No Known Activations