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. 1002
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal achievements and career milestones

    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
    +0.27
    0.9%
    1967
    +0.10
    0.3%
    1013
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    66
    +0.27
    0.04
    509
    +0.10
    0.04
    1967
    +0.08
    0.04
    Negative Logits
    <bos>
    -1.61
    exitRule
    -0.56
    HasIndex
    -0.55
    AsUp
    -0.54
    marshaller
    -0.53
     beheaded
    -0.53
    Дереккөздер
    -0.50
    исленность
    -0.50
    Personendaten
    -0.49
     ceded
    -0.49
    POSITIVE LOGITS
     Græ
    1.12
     kafe
    1.08
     monaster
    1.06
     silikon
    0.98
     Minang
    0.97
     seksi
    0.96
     cioc
    0.95
     keramik
    0.94
     ekos
    0.94
     broder
    0.92
    Activations Density 0.255%

    No Known Activations