© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 6065
    Prev
    Next
    INDEX
    Explanations

    conjunctions indicating contrast, specifically "but" and "not"

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    674
    +0.13
    0.4%
    1351
    +0.10
    0.3%
    555
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1677
    +0.13
    0.04
    555
    +0.10
    0.03
    356
    +0.10
    0.03
    Negative Logits
     depic
    -1.37
     increa
    -1.35
     reluct
    -1.32
     encomp
    -1.30
     maneu
    -1.29
     inev
    -1.28
     Juf
    -1.27
     Augu
    -1.27
     accla
    -1.27
     Intere
    -1.24
    POSITIVE LOGITS
    <bos>
    0.94
    
    0.70
    #
    0.70
    tagHelperRunner
    0.66
    /**
    0.64
    ValueStyle
    0.63
    <?
    0.62
    Producción
    0.62
     nonetheless
    0.61
    ectoria
    0.61
    Activations Density 0.171%

    No Known Activations