© 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. 13768
    Prev
    Next
    INDEX
    Explanations

    descriptive words related to a person's character

    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
    +0.11
    0.3%
    605
    +0.10
    0.3%
    940
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    605
    +0.11
    0.02
    1446
    +0.10
    0.04
    1528
    +0.07
    0.04
    Negative Logits
     Intere
    -1.98
     inev
    -1.95
     mef
    -1.92
     dises
    -1.91
     makro
    -1.89
     seiz
    -1.88
     wien
    -1.87
     Keny
    -1.84
     squa
    -1.83
     oner
    -1.83
    POSITIVE LOGITS
     compassionate
    0.70
     always
    0.69
     caring
    0.68
     personality
    0.68
    strictEqual
    0.67
     kindness
    0.66
     loves
    0.66
     compassion
    0.66
     willing
    0.65
     love
    0.65
    Activations Density 0.547%

    No Known Activations