© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 10550
    Prev
    Next
    INDEX
    Explanations

    instances of the word "appear" or variations of it

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    316
    +0.15
    0.5%
    971
    +0.14
    0.5%
    1413
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.15
    0.05
    971
    +0.14
    0.04
    1515
    +0.11
    0.03
    Negative Logits
     perpé
    -0.67
     Sada
    -0.55
     Khart
    -0.54
     Quid
    -0.53
     proprement
    -0.51
     Quod
    -0.50
     Magister
    -0.50
     Soll
    -0.49
     Sall
    -0.49
     teras
    -0.48
    POSITIVE LOGITS
     appear
    1.07
     appeared
    0.98
     appearance
    0.97
     appearing
    0.96
    appear
    0.94
     appears
    0.93
     Appearance
    0.93
     APPE
    0.93
     Appear
    0.92
     appearances
    0.90
    Activations Density 0.087%

    No Known Activations