© 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. 3910
    Prev
    Next
    INDEX
    Explanations

    words related to timing within a game or event

    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
    1416
    +0.10
    0.3%
    856
    +0.10
    0.3%
    559
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    559
    +0.10
    0.03
    856
    +0.10
    0.03
    1686
    +0.10
    0.04
    Negative Logits
    Glej
    -0.69
     pymysql
    -0.63
     NUKAT
    -0.58
    Sklici
    -0.57
     Bardzo
    -0.57
    Πηγές
    -0.55
     LoginForm
    -0.54
     actionTypes
    -0.53
    Și
    -0.53
     trouvera
    -0.53
    POSITIVE LOGITS
     cyr
    0.79
     textil
    0.63
     vort
    0.62
     reputa
    0.61
     anse
    0.60
     apartament
    0.59
     gymnas
    0.59
     utop
    0.58
     augus
    0.57
     luf
    0.57
    Activations Density 0.189%

    No Known Activations