© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 827
    Prev
    Next
    INDEX
    Explanations

    terms related to drama and dramatic tension

    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
    1921
    +0.15
    0.6%
    1464
    +0.14
    0.5%
    1392
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1921
    +0.15
    0.03
    538
    +0.14
    0.03
    1392
    +0.13
    0.03
    Negative Logits
     indé
    -0.55
     Obtener
    -0.52
     secr
    -0.52
     Candice
    -0.52
    OGND
    -0.50
     reflexion
    -0.50
     bicarbon
    -0.49
     Ejemplo
    -0.48
     considér
    -0.47
     dilap
    -0.47
    POSITIVE LOGITS
     drama
    1.22
    dramatic
    1.08
    drama
    1.05
     dramatic
    1.04
     dramas
    1.04
     Drama
    1.00
    Drama
    0.98
    Dramatic
    0.85
     Dramatic
    0.83
     dram
    0.77
    Activations Density 0.081%

    No Known Activations