© 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. 1050
    Prev
    Next
    INDEX
    Explanations

    phrases related to impatience and time management

    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
    +0.26
    1.0%
    1224
    +0.07
    0.3%
    1253
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1253
    +0.26
    0.04
    17
    +0.07
    0.09
    1772
    +0.07
    0.06
    Negative Logits
    <bos>
    -2.56
    ⓧ
    -0.89
    /***
    -0.88
     intersper
    -0.87
     amass
    -0.86
     disbur
    -0.81
    /*!
    -0.74
    //---
    -0.74
     disarm
    -0.72
     rouse
    -0.70
    POSITIVE LOGITS
     silikon
    1.14
     seksi
    1.07
     mikrofon
    1.05
     lele
    1.05
     autunno
    1.02
     riva
    1.02
     kafe
    1.01
     soulign
    1.01
     maksi
    0.99
     kasa
    0.98
    Activations Density 2.449%

    No Known Activations