© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 14769
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "pace" in a text, particularly in the context of different discussions

    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
    75
    +0.13
    0.5%
    971
    +0.12
    0.4%
    1350
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    75
    +0.13
    0.02
    404
    +0.12
    0.02
    1059
    +0.11
    0.01
    Negative Logits
    Tir
    -0.46
    bln
    -0.45
     Atra
    -0.45
     Senza
    -0.44
    Griff
    -0.43
     Tir
    -0.43
    Hew
    -0.43
     Kug
    -0.42
    Bila
    -0.42
     Vand
    -0.42
    POSITIVE LOGITS
     pace
    1.38
     Pace
    1.20
    Pace
    1.12
     paced
    1.10
     pacing
    1.00
    paced
    0.95
     PACE
    0.92
     paces
    0.90
    pace
    0.90
     friable
    0.79
    Activations Density 0.051%

    No Known Activations