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. 6828
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be" and their variations in different tenses

    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
    +0.28
    1.3%
    1974
    +0.11
    0.5%
    1637
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    950
    +0.28
    0.05
    438
    +0.11
    0.05
    1974
    +0.10
    0.04
    Negative Logits
    <bos>
    -1.99
     perpetuate
    -0.57
     amass
    -0.55
     modernize
    -0.54
     mobilize
    -0.54
     unify
    -0.53
     condense
    -0.53
     disbur
    -0.52
     assimilate
    -0.52
     neutralize
    -0.51
    POSITIVE LOGITS
     jawa
    1.14
     Minang
    1.13
     Pekan
    1.09
     Muhamma
    1.08
     jaya
    1.07
     Jambi
    1.07
     bandung
    1.06
     Bekasi
    1.06
     Banjar
    1.02
     nikah
    0.98
    Activations Density 0.093%

    No Known Activations