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. 12651
    Prev
    Next
    INDEX
    Explanations

    guitar riffs and musical elements related to guitar playing

    oai_token-act-pair · gpt-3.5-turbo

    musical elements related to guitar riffs and compositions

    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
     Expend
    -0.83
     indemn
    -0.81
     Samar
    -0.74
     Govern
    -0.73
     Loyal
    -0.71
     Redemption
    -0.70
     Pri
    -0.69
     Pyr
    -0.68
     Genetic
    -0.68
     Gawker
    -0.67
    POSITIVE LOGITS
     chords
    1.20
     sax
    1.19
     melody
    1.14
     piano
    1.13
    tones
    1.09
     melodies
    1.07
     guitar
    1.07
     rhythms
    1.06
    itars
    1.05
     orchestra
    1.02
    Activations Density 0.162%

    No Known Activations