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. 892
    Prev
    Next
    INDEX
    Explanations

    references to the publication "Forbes."

    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
    1604
    +0.17
    0.9%
    893
    +0.14
    0.8%
    757
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.17
    0.03
    757
    +0.14
    0.02
    893
    +0.14
    0.02
    Negative Logits
    <bos>
    -1.20
    Linki
    -0.69
    /**
    
    
    -0.69
    bibnamefont
    -0.66
    textTheme
    -0.63
    ngrx
    -0.63
     يتيمه
    -0.61
     Trotzdem
    -0.59
    Referències
    -0.59
     pinulongan
    -0.59
    POSITIVE LOGITS
     Forbes
    1.41
     magis
    1.32
    Forbes
    1.27
     haup
    1.25
     ftre
    1.24
     fua
    1.23
     vns
    1.22
     kuro
    1.21
     jaya
    1.19
     Minang
    1.18
    Activations Density 0.185%

    No Known Activations