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. 10-RES-JB
    6. 658
    Prev
    Next
    INDEX
    Explanations

    references to the name "Mul" in contexts related to people or characters

    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
    795
    +0.17
    0.9%
    1276
    +0.14
    0.8%
    920
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    795
    +0.17
    0.02
    1276
    +0.14
    0.02
    58
    +0.13
    0.01
    Negative Logits
    <bos>
    -1.76
    //};
    -0.65
    ImageField
    -0.63
    setClass
    -0.60
    LinkedHashMap
    -0.59
    PerformLayout
    -0.58
    Atoi
    -0.58
     ++)
    -0.56
    makeText
    -0.55
    ApiOperation
    -0.53
    POSITIVE LOGITS
     Mul
    1.47
    Mul
    1.28
     MUL
    1.24
     maneu
    1.19
     mul
    1.18
     Juf
    1.10
     excru
    1.09
     inev
    1.08
     soulign
    1.05
     Hez
    1.04
    Activations Density 0.116%

    No Known Activations