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 · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 12-RES-JB
    6. 177
    Prev
    Next
    INDEX
    Explanations

    references to musical performances and standards, particularly in the jazz genre

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.12.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    12
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.32
    1.1%
    1842
    +0.16
    0.5%
    1823
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1823
    +0.32
    0.05
    678
    +0.16
    0.04
    793
    +0.08
    0.04
    Negative Logits
    <bos>
    -1.85
    <?
    -0.77
    tangentMode
    -0.73
    ANDUM
    -0.70
    BUYER
    -0.70
     EconPapers
    -0.68
    /**
    -0.68
    ⓧ
    -0.67
    /*
    -0.66
    uxxxx
    -0.66
    POSITIVE LOGITS
     maneu
    2.09
     Juf
    2.05
     reluct
    2.04
     increa
    2.00
     affor
    1.96
     milf
    1.92
     disagre
    1.91
     impra
    1.90
     aen
    1.89
     inev
    1.88
    Activations Density 0.367%

    No Known Activations