© 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. 13437
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a firm opinion or viewpoint

    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
    1842
    +0.17
    0.5%
    468
    +0.14
    0.4%
    394
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    599
    +0.17
    0.07
    468
    +0.14
    0.05
    1958
    +0.11
    0.05
    Negative Logits
     conspic
    -1.01
     uncin
    -0.94
    <bos>
    -0.94
     desir
    -0.92
     dsg
    -0.89
     antem
    -0.89
     effe
    -0.88
     coar
    -0.88
     inext
    -0.87
     lamborghini
    -0.86
    POSITIVE LOGITS
     …
    0.52
    ={`/
    0.50
     ...
    0.50
     fucked
    0.48
     deeply
    0.46
    ínguez
    0.46
     [
    0.46
    Tôi
    0.45
     utilizarse
    0.45
     my
    0.45
    Activations Density 0.631%

    No Known Activations