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. 6815
    Prev
    Next
    INDEX
    Explanations

    references to illegal activities and substances

    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
    +0.21
    0.8%
    1013
    +0.15
    0.5%
    1150
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1013
    +0.21
    0.13
    1870
    +0.15
    0.06
    647
    +0.14
    0.05
    Negative Logits
    <bos>
    -1.13
     dras
    -0.63
     solidar
    -0.61
    Cependant
    -0.61
     impon
    -0.60
     utop
    -0.59
     instan
    -0.59
    endwhile
    -0.58
     tenden
    -0.58
    DataPropertyName
    -0.57
    POSITIVE LOGITS
     embodi
    1.06
     Silurian
    1.03
     Shakspeare
    1.03
     tramonto
    1.02
     soggior
    1.02
     unwarran
    1.00
     soulign
    0.99
     paradiso
    0.99
     ecru
    0.96
     clô
    0.95
    Activations Density 1.127%

    No Known Activations