© 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. 4405
    Prev
    Next
    INDEX
    Explanations

    mentions of pilot programs or projects in different contexts

    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
    1865
    +0.16
    0.6%
    1691
    +0.14
    0.6%
    1757
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1865
    +0.16
    0.02
    1778
    +0.14
    0.02
    1691
    +0.14
    0.02
    Negative Logits
     ghe
    -0.78
     „,
    -0.71
     tsl
    -0.71
     lele
    -0.69
     laf
    -0.67
     aen
    -0.66
     fep
    -0.65
     &.
    -0.65
     fta
    -0.65
     kram
    -0.64
    POSITIVE LOGITS
     pilot
    1.40
    pilot
    1.26
     pilots
    1.25
     Pilot
    1.25
    Pilot
    1.23
     Pilots
    1.08
     PILOT
    1.06
     Pil
    0.94
    Pil
    0.93
     pil
    0.90
    Activations Density 0.067%

    No Known Activations