© 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. 6755
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal issues and governmental actions

    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
    1278
    +0.07
    0.2%
    1055
    +0.07
    0.2%
    247
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1055
    +0.07
    0.04
    247
    +0.07
    0.04
    1278
    +0.07
    0.04
    Negative Logits
     emphat
    -0.91
     indestru
    -0.90
     inconce
    -0.89
     disagre
    -0.84
     macrop
    -0.83
     vagu
    -0.83
     desir
    -0.79
     indescri
    -0.78
     fuf
    -0.77
     apprehen
    -0.77
    POSITIVE LOGITS
    <bos>
    0.71
     foreseeable
    0.71
    HasAnnotation
    0.60
     unless
    0.56
     anytime
    0.55
    unless
    0.55
     akut
    0.54
     anywhere
    0.53
    المشاركات
    0.53
     tienden
    0.52
    Activations Density 0.259%

    No Known Activations