© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2583
    Prev
    Next
    INDEX
    Explanations

    terms related to organic products

    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
    50
    +0.08
    0.3%
    1233
    +0.07
    0.3%
    1837
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1586
    +0.08
    0.04
    1233
    +0.07
    0.03
    1765
    +0.06
    0.03
    Negative Logits
    <bos>
    -0.99
    /**
    -0.75
    <?
    -0.75
    
    -0.74
    public
    -0.72
     put
    -0.66
    ⓧ
    -0.65
    <?
    -0.64
     also
    -0.61
    <eos>
    -0.61
    POSITIVE LOGITS
     organic
    2.22
     Organic
    2.10
    Organic
    2.07
     ORGANIC
    2.04
    organic
    1.99
     organics
    1.74
     ftu
    1.72
     aen
    1.70
     fta
    1.65
     vns
    1.63
    Activations Density 0.118%

    No Known Activations