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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 5174
    Prev
    Next
    INDEX
    Explanations

    information related to filling out forms, particularly for military veterans

    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
    +0.15
    0.6%
    411
    +0.09
    0.4%
    789
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    411
    +0.15
    0.08
    1334
    +0.09
    0.08
    1328
    +0.09
    0.09
    Negative Logits
    <bos>
    -2.77
    ⓧ
    -1.09
     intersper
    -0.96
    /**
    -0.94
    <?
    -0.88
    
    
    -0.78
     endow
    -0.73
    /***
    
    -0.71
     endeavored
    -0.70
     amass
    -0.67
    POSITIVE LOGITS
     dott
    0.71
     combusti
    0.70
     amplific
    0.68
     chiunque
    0.63
     cias
    0.63
     perpétu
    0.62
     réput
    0.61
     eviden
    0.61
     resalt
    0.60
     auguri
    0.60
    Activations Density 1.257%

    No Known Activations