© 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. 6906
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing reassurance and advice

    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
    1473
    +0.13
    0.4%
    674
    +0.12
    0.3%
    446
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1473
    +0.13
    0.03
    1358
    +0.12
    0.04
    446
    +0.08
    0.03
    Negative Logits
     meras
    -0.84
     antik
    -0.75
     republi
    -0.71
     ortop
    -0.70
     Singapur
    -0.70
     dichi
    -0.69
     doman
    -0.69
     monaster
    -0.67
     keten
    -0.67
     geograf
    -0.66
    POSITIVE LOGITS
    <bos>
    0.94
     friable
    0.58
     there
    0.58
     blackish
    0.55
     purplish
    0.54
     tassels
    0.54
     těch
    0.53
     nachher
    0.52
     tassel
    0.52
     écrivain
    0.51
    Activations Density 0.136%

    No Known Activations