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. 5379
    Prev
    Next
    INDEX
    Explanations

    mentions of the state of Arizona

    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
    1921
    +0.20
    1.0%
    1178
    +0.16
    0.9%
    1124
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1921
    +0.20
    0.06
    1178
    +0.16
    0.04
    479
    +0.14
    0.04
    Negative Logits
    <bos>
    -1.96
    ⓧ
    -0.93
    <?
    -0.75
    
    
    -0.71
    Iné
    -0.66
    lepiej
    -0.65
    bardziej
    -0.61
    UTERS
    -0.61
    /*
    -0.61
    Vea
    -0.60
    POSITIVE LOGITS
     wien
    1.56
     lele
    1.43
     meis
    1.43
     aen
    1.41
     arizona
    1.39
     bayern
    1.37
     tempe
    1.37
     Münch
    1.33
     mef
    1.33
     marseille
    1.32
    Activations Density 0.378%

    No Known Activations