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. 9-RES-JB
    6. 22152
    Prev
    Next
    INDEX
    Explanations

    mentions of famous composers or classical music terms, particularly focusing on Beethoven

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Beethoven

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sabha
    -0.68
     slot
    -0.67
     unexpl
    -0.61
     invari
    -0.60
     expenditure
    -0.59
     AMA
    -0.57
     Malays
    -0.55
     Cortex
    -0.55
     pave
    -0.55
     constitu
    -0.55
    POSITIVE LOGITS
    lehem
    0.97
    zeb
    0.94
    oven
    0.89
    avior
    0.84
    ãĥĦ
    0.81
    athering
    0.80
    chuk
    0.80
    iful
    0.76
    zee
    0.76
    qt
    0.75
    Activations Density 0.101%

    No Known Activations