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. 3581
    Prev
    Next
    INDEX
    Explanations

    references to orchestral music and composers, particularly with a focus on Beethoven

    oai_token-act-pair · gpt-3.5-turbo

    terms related to orchestral music and composers

    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
     Meth
    -0.74
     Coke
    -0.69
     Gamer
    -0.67
    holders
    -0.66
    resp
    -0.64
     McCl
    -0.63
     Depot
    -0.63
    holder
    -0.63
     Territories
    -0.63
     Protein
    -0.62
    POSITIVE LOGITS
     violin
    1.25
     pian
    1.22
     orchestra
    1.18
     sax
    1.15
     piano
    1.12
     Orchestra
    1.11
     composer
    1.04
     Piano
    1.03
     orchestr
    0.96
     ballet
    0.91
    Activations Density 0.051%

    No Known Activations