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. 900
    Prev
    Next
    INDEX
    Explanations

    terms associated with the concept of devaluation or undermining worth

    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
    +0.19
    1.1%
    1145
    +0.16
    0.9%
    1404
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1145
    +0.19
    0.04
    1404
    +0.16
    0.04
    900
    +0.13
    0.03
    Negative Logits
    <bos>
    -2.51
     springfox
    -0.81
    <?
    
    -0.68
    /*++
    -0.61
     disbur
    -0.60
     banish
    -0.59
    awsze
    -0.58
     signore
    -0.55
     proprietario
    -0.55
    tská
    -0.54
    POSITIVE LOGITS
     Rine
    1.09
     soulign
    1.07
     Dewi
    1.04
    De
    1.04
     compréhen
    1.04
     Deh
    1.02
     Deg
    1.02
     De
    1.00
     véhic
    0.99
     Dede
    0.99
    Activations Density 0.132%

    No Known Activations