© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 12788
    Prev
    Next
    INDEX
    Explanations

    phrases relating to communication and information sharing

    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
    1343
    +0.12
    0.4%
    1415
    +0.09
    0.3%
    674
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1415
    +0.12
    0.05
    1836
    +0.09
    0.02
    1477
    +0.08
    0.04
    Negative Logits
     Trasp
    -0.79
     alip
    -0.78
     miu
    -0.77
     fta
    -0.75
     susun
    -0.73
     tanga
    -0.73
     compréhen
    -0.72
     kani
    -0.71
     ··
    -0.71
     soigne
    -0.70
    POSITIVE LOGITS
     remind
    0.81
     ویکی‌پدیای
    0.68
     clarify
    0.67
     note
    0.66
     reiterate
    0.66
     reminder
    0.65
     warn
    0.63
     assure
    0.63
     reminding
    0.60
     emphasize
    0.59
    Activations Density 0.246%

    No Known Activations