© 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. 10-RES-JB
    11. 4219
    Prev
    Next
    INDEX
    Explanations

    names related to people and places, particularly focusing on last names or notable figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1023
    +0.20
    1.0%
    662
    +0.16
    0.8%
    1334
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1097
    +0.20
    0.08
    227
    +0.16
    0.07
    1741
    +0.14
    0.01
    Negative Logits
    <bos>
    -1.53
    AnchorStyles
    -0.81
     NSCoder
    -0.74
    Autoritní
    -0.72
    EndInit
    -0.71
    PerformLayout
    -0.70
    elemField
    -0.68
    IsMutable
    -0.68
    RegressionTest
    -0.68
    LEncoder
    -0.67
    POSITIVE LOGITS
     milf
    1.66
     shenan
    1.59
     wikihow
    1.49
     snoopy
    1.45
     „,
    1.44
     ftu
    1.43
     wattpad
    1.43
     indestru
    1.41
     blackpink
    1.39
     !...
    1.39
    Activations Density 0.319%

    No Known Activations