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. 0-RES-JB
    6. 3742
    Prev
    Next
    INDEX
    Explanations

    words related to metallic brass instruments

    oai_token-act-pair · gpt-3.5-turbo

    references to 'brass' in various contexts, particularly in relation to military or leadership roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     impair
    -0.79
     Vale
    -0.75
    uras
    -0.75
     Cait
    -0.65
    ivid
    -0.65
    States
    -0.64
    onomous
    -0.64
    EE
    -0.63
    row
    -0.63
    lement
    -0.63
    POSITIVE LOGITS
     brass
    4.00
     Brass
    2.49
     nylon
    1.08
     percussion
    1.08
     stainless
    1.05
     finest
    1.00
     trumpet
    0.95
     zinc
    0.94
     bronze
    0.94
     chrome
    0.92
    Activations Density 0.020%

    No Known Activations