© 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. 13276
    Prev
    Next
    INDEX
    Explanations

    complex and gripping storylines in video games

    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
    872
    +0.13
    0.4%
    599
    +0.12
    0.3%
    194
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1598
    +0.13
    0.02
    24
    +0.12
    0.04
    872
    +0.10
    0.05
    Negative Logits
     recueil
    -0.70
     dégust
    -0.68
     anhyd
    -0.66
     récon
    -0.64
     bonté
    -0.64
     amitié
    -0.63
     renou
    -0.62
     écout
    -0.59
     vêtement
    -0.57
     imprimée
    -0.57
    POSITIVE LOGITS
     storyline
    0.80
     storylines
    0.74
     narrative
    0.72
     story
    0.72
     plot
    0.60
     storytelling
    0.59
     narr
    0.58
     narratives
    0.58
    plot
    0.57
     backstory
    0.57
    Activations Density 0.398%

    No Known Activations