© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 6428
    Prev
    Next
    INDEX
    Explanations

    instances where characters laugh or display emotion

    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
    1531
    +0.12
    0.3%
    1269
    +0.09
    0.3%
    438
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1269
    +0.12
    0.05
    1531
    +0.09
    0.04
    1001
    +0.09
    0.04
    Negative Logits
     „,
    -1.05
     fta
    -1.03
     emphat
    -1.03
     effe
    -1.03
     fte
    -1.00
     Bibl
    -0.99
     mef
    -0.98
     Juf
    -0.97
     inev
    -0.96
     gend
    -0.96
    POSITIVE LOGITS
     nonetheless
    0.78
     nevertheless
    0.69
     still
    0.57
     otherwise
    0.57
     digress
    0.55
    offsetWidth
    0.52
    +":
    0.52
     fühlte
    0.50
     sahen
    0.49
     voegen
    0.49
    Activations Density 0.669%

    No Known Activations