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. 8437
    Prev
    Next
    INDEX
    Explanations

    terms related to the word "Sound"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Sound" related to locations or entities

    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
    assetsadobe
    -0.80
    agher
    -0.74
    ONT
    -0.71
    utations
    -0.70
    20439
    -0.70
    isin
    -0.69
    olson
    -0.69
    perty
    -0.69
    arian
    -0.67
     pall
    -0.67
    POSITIVE LOGITS
    track
    1.19
    tracks
    1.07
    wave
    1.02
     Blaster
    0.98
     Sound
    0.97
    Sounds
    0.93
     Sounds
    0.92
    Cloud
    0.86
    sound
    0.85
    Sound
    0.84
    Activations Density 0.015%

    No Known Activations