© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 6446
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant roles or impacts in different contexts

    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
    332
    +0.09
    0.2%
    1013
    +0.09
    0.2%
    636
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    636
    +0.09
    0.04
    1372
    +0.09
    0.04
    509
    +0.08
    0.04
    Negative Logits
     emphat
    -1.67
     accla
    -1.57
     increa
    -1.54
     fta
    -1.50
     purcha
    -1.49
     strick
    -1.49
     suscep
    -1.48
     fuf
    -1.46
     affor
    -1.44
     inev
    -1.44
    POSITIVE LOGITS
    ในการ
    0.71
     towards
    0.65
     in
    0.63
     toward
    0.62
    于
    0.59
     contribution
    0.57
     on
    0.57
    factor
    0.56
    ChatColor
    0.56
     regarding
    0.56
    Activations Density 0.175%

    No Known Activations