© 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. 2295
    Prev
    Next
    INDEX
    Explanations

    references to the word "elephant"

    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
    517
    +0.11
    0.3%
    168
    +0.10
    0.3%
    890
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.11
    0.03
    690
    +0.10
    0.04
    1120
    +0.09
    0.03
    Negative Logits
    <bos>
    -0.88
     löyty
    -0.57
     pysty
    -0.55
    <?
    -0.53
     lumea
    -0.52
     rehabilitate
    -0.52
    
    -0.52
     todella
    -0.51
     awakens
    -0.50
     tilbage
    -0.50
    POSITIVE LOGITS
     elephant
    1.88
     Elephant
    1.87
    Elephant
    1.69
    elephant
    1.69
     elephants
    1.64
     Elephants
    1.62
     Ivory
    1.61
     ivory
    1.57
     elef
    1.55
    Ivory
    1.53
    Activations Density 0.274%

    No Known Activations