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. 1135
    Prev
    Next
    INDEX
    Explanations

    numerical values related to political or organizational data

    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
    1.1%
    776
    +0.15
    0.6%
    1978
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    776
    +0.28
    0.08
    1978
    +0.15
    0.07
    499
    +0.15
    0.06
    Negative Logits
    <bos>
    -2.75
     endow
    -0.75
     intersper
    -0.73
     endeavored
    -0.73
     endeavoured
    -0.72
     disbur
    -0.69
     strove
    -0.69
     rejoined
    -0.67
     nadzie
    -0.66
     realises
    -0.65
    POSITIVE LOGITS
     kosme
    1.12
     silikon
    1.12
     keramik
    1.11
     monaster
    1.09
     Strukt
    1.09
     sappi
    1.09
     Trasp
    1.08
     alkoh
    1.07
     kollek
    1.04
     praktik
    1.04
    Activations Density 0.165%

    No Known Activations