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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 2-RES-JB
    6. 2929
    Prev
    Next
    INDEX
    Explanations

    mentions of drum-related terms and actions

    oai_token-act-pair · gpt-3.5-turbo

    references to drums and drumming-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Agency
    -0.75
     Upton
    -0.65
    ################
    -0.64
     Kiw
    -0.64
    hiro
    -0.62
     Morales
    -0.61
     Australians
    -0.61
     Mandela
    -0.60
     Hitman
    -0.59
     Tasman
    -0.59
    POSITIVE LOGITS
     drums
    1.08
     drum
    1.05
    mers
    0.98
    ming
    0.95
    sticks
    0.94
    beat
    0.90
    ette
    0.90
    sonian
    0.89
     Drum
    0.84
    ettes
    0.84
    Activations Density 0.010%

    No Known Activations