© 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. 7523
    Prev
    Next
    INDEX
    Explanations

    references to social status, wealth, and prestigious lifestyle

    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
    198
    +0.12
    0.3%
    1385
    +0.10
    0.3%
    1485
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.12
    0.05
    756
    +0.10
    0.05
    1485
    +0.09
    0.03
    Negative Logits
     apprehen
    -0.93
     tyn
    -0.83
     simplif
    -0.82
     ineffec
    -0.80
     disgra
    -0.79
     autob
    -0.78
     eiffel
    -0.78
     riviera
    -0.78
     bordeaux
    -0.77
     matel
    -0.76
    POSITIVE LOGITS
     luxury
    0.79
     luxurious
    0.70
     wealthy
    0.69
     affluent
    0.60
     elite
    0.60
     upscale
    0.59
     privilege
    0.59
     Luxury
    0.59
     expensive
    0.56
     mansion
    0.56
    Activations Density 0.665%

    No Known Activations