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-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 16019
    Prev
    Next
    INDEX
    Explanations

    descriptions and details about restaurants or food spots

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    453
    +0.33
    1.1%
    674
    +0.19
    0.6%
    1510
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.33
    0.02
    453
    +0.19
    0.09
    1613
    +0.16
    0.05
    Negative Logits
     bourgeo
    -1.72
     EEU
    -1.67
     unlaw
    -1.66
     pamph
    -1.63
     volunte
    -1.63
     impractica
    -1.62
     Juf
    -1.61
     „,
    -1.55
     Abbé
    -1.53
     philanth
    -1.52
    POSITIVE LOGITS
    <bos>
    1.12
    押
    0.60
     
    0.58
    本
    0.58
    riwal
    0.58
      
    0.58
    督
    0.57
    散
    0.57
    \
    0.57
    生
    0.56
    Activations Density 1.523%

    No Known Activations