© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 5818
    Prev
    Next
    INDEX
    Explanations

    time-related phrases, particularly related to spending time or going through books

    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
    +0.22
    0.9%
    1013
    +0.10
    0.4%
    1413
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1013
    +0.22
    0.06
    369
    +0.10
    0.04
    1041
    +0.09
    0.04
    Negative Logits
    <bos>
    -2.69
    ⓧ
    -0.80
    /**
    -0.79
    addCriterion
    -0.66
    add
    -0.66
    <?
    -0.64
    class
    -0.61
    
    -0.59
    setClass
    -0.59
     regulate
    -0.58
    POSITIVE LOGITS
     lamborghini
    1.26
     venice
    1.24
     reft
    1.23
     perfon
    1.23
     fatis
    1.22
     chrysler
    1.22
     fays
    1.21
     errone
    1.20
     dises
    1.20
     ftu
    1.19
    Activations Density 0.420%

    No Known Activations