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. 6-RES-JB
    6. 2389
    Prev
    Next
    INDEX
    Explanations

    terms related to utility, specifically in the context of budgeting or operational activities

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.16
    1.0%
    1103
    +0.13
    0.8%
    1708
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1708
    +0.16
    0.03
    662
    +0.13
    0.02
    1624
    +0.12
    0.02
    Negative Logits
    <bos>
    -3.01
    /***
    
    -0.66
    //---
    -0.62
    //--
    -0.60
     defray
    -0.59
     evacuate
    -0.58
    principalColumn
    -0.57
     disbur
    -0.53
     leave
    -0.53
    //----
    -0.52
    POSITIVE LOGITS
     Utility
    1.26
     utility
    1.23
     utilities
    1.18
     Græ
    1.16
     riva
    1.14
     tramont
    1.13
     Utilities
    1.11
     cæ
    1.09
     shutterstock
    1.06
     saar
    1.05
    Activations Density 0.145%

    No Known Activations