© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 1292
    Prev
    Next
    INDEX
    Explanations

    terms related to IP (Internet Protocol) addresses

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1387
    +0.12
    0.4%
    50
    +0.08
    0.3%
    101
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1387
    +0.12
    0.04
    1121
    +0.08
    0.03
    711
    +0.07
    0.03
    Negative Logits
    <bos>
    -0.87
     поло
    -0.71
     gain
    -0.66
            
    -0.65
     become
    -0.65
                    
    -0.64
              
    -0.64
        
    -0.64
     were
    -0.63
                
    -0.63
    POSITIVE LOGITS
     IP
    2.28
     IPs
    2.15
     Ip
    2.10
     stockholm
    2.04
     maneu
    2.02
     ip
    1.96
    IP
    1.96
     Juf
    1.83
    Ip
    1.76
     inev
    1.75
    Activations Density 0.138%

    No Known Activations