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. 15504
    Prev
    Next
    INDEX
    Explanations

    technical terms related to data structures or coding conventions

    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
    50
    +0.32
    1.3%
    394
    +0.16
    0.7%
    1177
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.32
    0.10
    50
    +0.16
    0.08
    678
    +0.15
    0.07
    Negative Logits
    <bos>
    -1.33
                
    -0.65
    ).
    -0.64
    ──
    -0.64
                   
    -0.62
                    
    -0.62
            
    -0.62
                        
    -0.62
               
    -0.61
                            
    -0.61
    POSITIVE LOGITS
     disagre
    2.15
     impra
    2.15
     increa
    2.13
     affor
    2.11
     reluct
    2.09
     uninten
    2.03
     inev
    2.02
     impractica
    2.01
     unwarran
    1.99
     aen
    1.97
    Activations Density 0.711%

    No Known Activations