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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 739
    Prev
    Next
    INDEX
    Explanations

    musical genres and their characteristics

    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.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.23
    0.9%
    1870
    +0.16
    0.6%
    1013
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.23
    0.04
    678
    +0.16
    0.05
    74
    +0.10
    0.04
    Negative Logits
    <bos>
    -2.28
    principalTable
    -0.95
    principalColumn
    -0.93
     Paglinawan
    -0.93
     GeoNames
    -0.88
     censiti
    -0.87
     Wikimédia
    -0.85
    HasIndex
    -0.85
     consultato
    -0.85
     ***!
    -0.83
    POSITIVE LOGITS
     increa
    2.01
     affor
    1.92
     impra
    1.92
     maneu
    1.85
     reluct
    1.82
     Juf
    1.79
     emphat
    1.78
     unspeak
    1.78
     unden
    1.77
     disagre
    1.77
    Activations Density 0.321%

    No Known Activations