© 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. 3489
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate observation or reporting, particularly in a narrative context

    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
    184
    +0.31
    1.2%
    50
    +0.14
    0.6%
    2019
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.31
    0.03
    453
    +0.14
    0.04
    147
    +0.14
    0.02
    Negative Logits
    <bos>
    -3.33
    Autoritní
    -1.28
    oredCriteria
    -0.99
     Roskov
    -0.99
    Vidite
    -0.92
    Rujuakan
    -0.90
     Italijani
    -0.88
    Panamoan
    -0.86
     Administrativna
    -0.85
    contentLoaded
    -0.83
    POSITIVE LOGITS
     vété
    1.08
     insensible
    1.04
     disgra
    1.02
     immor
    1.02
     parch
    1.01
     illi
    0.95
     indestru
    0.92
     alre
    0.92
     unden
    0.90
     reluct
    0.90
    Activations Density 0.318%

    No Known Activations