© 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. 12214
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'and'

    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
    2019
    +0.10
    0.3%
    382
    +0.10
    0.3%
    994
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1446
    +0.10
    0.04
    1806
    +0.10
    0.04
    1413
    +0.10
    0.03
    Negative Logits
     alip
    -1.26
     kani
    -1.23
     typique
    -1.17
     abstrait
    -1.17
     régulier
    -1.15
     kasa
    -1.14
     Juf
    -1.11
     expéri
    -1.08
     réaliste
    -1.05
     pama
    -1.05
    POSITIVE LOGITS
     efficient
    0.65
     powerful
    0.62
     accurate
    0.61
     durable
    0.61
    rogens
    0.61
     profitable
    0.61
     effective
    0.60
     consistent
    0.60
     reliable
    0.59
     impressive
    0.59
    Activations Density 0.165%

    No Known Activations