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

    Neuronpedia

    Jacobian LensNEW
    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. 14846
    Prev
    Next
    INDEX
    Explanations

    financial and legal terms related to property

    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
    481
    +0.14
    0.6%
    871
    +0.14
    0.6%
    1222
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.14
    0.03
    871
    +0.14
    0.03
    976
    +0.13
    0.03
    Negative Logits
     repug
    -0.86
     reluct
    -0.86
     impractica
    -0.82
     sovere
    -0.82
     affor
    -0.81
     viciss
    -0.80
     fuf
    -0.80
     increa
    -0.79
     guarante
    -0.76
     inev
    -0.75
    POSITIVE LOGITS
     property
    1.44
     Property
    1.34
    property
    1.32
    Property
    1.23
     properties
    1.21
     PROPERTY
    1.17
     Properties
    1.10
    properties
    1.08
    PROPERTY
    1.07
    getProperty
    1.03
    Activations Density 0.054%

    No Known Activations