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. 1241
    Prev
    Next
    INDEX
    Explanations

    terms related to economic warnings and financial instability

    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
    1.0%
    604
    +0.15
    0.5%
    764
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1531
    +0.27
    0.05
    1432
    +0.15
    0.05
    764
    +0.11
    0.03
    Negative Logits
    <bos>
    -3.06
    //*/
    -0.68
    Personendaten
    -0.67
    //----
    -0.59
    Referències
    -0.58
    ⓧ
    -0.58
     connect
    -0.57
    बाह
    -0.56
    StoreMessageInfo
    -0.56
    //---
    -0.55
    POSITIVE LOGITS
     actionTypes
    1.23
     panama
    1.20
     riviera
    1.18
     oleo
    1.17
     ecru
    1.17
     rancho
    1.17
     stockholm
    1.15
     Batam
    1.14
     Jambi
    1.13
     barcelona
    1.11
    Activations Density 0.873%

    No Known Activations