© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2891
    Prev
    Next
    INDEX
    Explanations

    instances of enjoyment or the act of enjoying something

    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
    +0.27
    1.5%
    1624
    +0.15
    0.9%
    783
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1624
    +0.27
    0.04
    783
    +0.15
    0.03
    1325
    +0.14
    0.03
    Negative Logits
    <bos>
    -2.88
    set
    -0.81
    vec
    -0.79
    dot
    -0.79
    public
    -0.78
    socket
    -0.77
    case
    -0.76
     set
    -0.73
    script
    -0.72
    line
    -0.72
    POSITIVE LOGITS
     maneu
    2.26
     stockholm
    2.19
     fta
    2.01
     impra
    2.01
     milf
    2.00
     scrat
    2.00
     increa
    1.99
     eiffel
    1.95
     affor
    1.94
     secon
    1.93
    Activations Density 0.064%

    No Known Activations