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. 4-RES-JB
    6. 5005
    Prev
    Next
    INDEX
    Explanations

    names or references related to the word "aud."

    oai_token-act-pair · gpt-3.5-turbo

    a specific phonetic pattern related to the sound "aud."

    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
     bis
    -0.79
     Helsinki
    -0.72
     Kai
    -0.68
     fumble
    -0.65
     LINE
    -0.65
     Stockholm
    -0.65
     Okinawa
    -0.65
     Dani
    -0.64
     Ragnarok
    -0.63
     Okin
    -0.63
    POSITIVE LOGITS
    ience
    1.01
    eatures
    1.01
    iences
    0.99
    aud
    0.94
    iosyn
    0.92
    enos
    0.90
    imentary
    0.90
    escription
    0.89
    ible
    0.88
    rey
    0.85
    Activations Density 0.005%

    No Known Activations