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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 6-RES-JB
    6. 14341
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to sound

    oai_token-act-pair · gpt-3.5-turbo

    references to sound, including descriptions and qualities of different sounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apsed
    -0.82
     Lann
    -0.79
    olkien
    -0.71
     Mandela
    -0.71
    hurst
    -0.68
     Restaur
    -0.65
    udeau
    -0.65
    aples
    -0.65
     Nort
    -0.65
     Osw
    -0.64
    POSITIVE LOGITS
    tracks
    1.16
    bite
    1.06
    lessly
    1.01
     vibrations
    0.92
    sound
    0.91
    proof
    0.89
    bytes
    0.88
    checks
    0.87
    atics
    0.84
     amplification
    0.83
    Activations Density 0.022%

    No Known Activations