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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 1581
    Prev
    Next
    INDEX
    Explanations

    references to individuals or the concept of "person" in various contexts

    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
    50
    +0.28
    1.7%
    1520
    +0.11
    0.7%
    25
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    513
    +0.28
    0.03
    1520
    +0.11
    0.03
    25
    +0.10
    0.03
    Negative Logits
    <bos>
    -2.71
     intersper
    -0.97
     banish
    -0.89
     endow
    -0.88
     cleave
    -0.85
     condense
    -0.84
     endeavored
    -0.82
     deflate
    -0.81
     infiltrate
    -0.80
     endeavoured
    -0.78
    POSITIVE LOGITS
     Person
    1.01
     person
    0.97
    Person
    0.95
    Persons
    0.94
     persons
    0.93
     Persons
    0.91
     PERSON
    0.89
     quoique
    0.88
    person
    0.87
     Quoi
    0.83
    Activations Density 0.048%

    No Known Activations