© 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. 7095
    Prev
    Next
    INDEX
    Explanations

    mentions of actions or qualities related to characters in a story or narrative

    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
    1446
    +0.07
    0.2%
    988
    +0.07
    0.2%
    1018
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    181
    +0.07
    0.04
    1693
    +0.07
    0.05
    16
    +0.06
    0.07
    Negative Logits
     intersper
    -1.23
     encomp
    -1.20
     depic
    -1.16
     reluct
    -1.14
     impra
    -1.12
     accla
    -1.11
     Keny
    -1.10
     emphat
    -1.10
     Intere
    -1.09
     snoopy
    -1.09
    POSITIVE LOGITS
     peaceful
    0.93
     calm
    0.87
     peacefully
    0.83
     gentle
    0.81
     benign
    0.75
     softer
    0.73
     harmless
    0.70
     peace
    0.67
     tranquil
    0.67
     calmly
    0.67
    Activations Density 1.019%

    No Known Activations