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. 659
    Prev
    Next
    INDEX
    Explanations

    significant incidents or actions related to sports, rescue efforts, or emergencies

    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%
    1842
    +0.17
    0.7%
    1013
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1013
    +0.23
    0.11
    1870
    +0.17
    0.05
    1745
    +0.15
    0.07
    Negative Logits
    <bos>
    -2.32
    Autoritní
    -0.89
     Italijani
    -0.79
     endwhile
    -0.78
    EndProject
    -0.74
    脚注の使い方
    -0.71
    UnifiedTopology
    -0.70
     &___
    -0.70
     Paglinawan
    -0.70
    Geplaatst
    -0.68
    POSITIVE LOGITS
     unlaw
    1.24
     affor
    1.20
     unspeak
    1.19
     pamph
    1.19
     impra
    1.19
     Juf
    1.16
     sovere
    1.16
     practition
    1.15
     impractica
    1.13
     maneu
    1.10
    Activations Density 0.727%

    No Known Activations