© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 1481
    Prev
    Next
    INDEX
    Explanations

    words related to loyalty and steadfastness

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1092
    +0.09
    0.2%
    699
    +0.07
    0.2%
    1350
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.09
    0.01
    1363
    +0.07
    0.03
    690
    +0.07
    0.03
    Negative Logits
    ラク
    -0.73
    operatorname
    -0.67
    ineno
    -0.67
     CreateTagHelper
    -0.66
    nodoc
    -0.65
    XtraEditors
    -0.65
    WriteAttribute
    -0.65
    IActionResult
    -0.65
    setContentType
    -0.65
    delwed
    -0.65
    POSITIVE LOGITS
     perfet
    1.99
     indestru
    1.93
     suspic
    1.84
     desir
    1.84
     effe
    1.83
     wien
    1.82
    ying
    1.79
     emphat
    1.78
     ftu
    1.77
     excru
    1.77
    Activations Density 0.249%

    No Known Activations