© 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. 16310
    Prev
    Next
    INDEX
    Explanations

    phrases related to statements, orders, and instructions

    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
    599
    +0.10
    0.3%
    319
    +0.07
    0.2%
    297
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    319
    +0.10
    0.04
    946
    +0.07
    0.04
    207
    +0.07
    0.04
    Negative Logits
     fta
    -1.36
     fte
    -1.30
     accla
    -1.26
     mef
    -1.25
     embra
    -1.23
     „,
    -1.21
     emphat
    -1.21
     fup
    -1.18
     wien
    -1.18
     inev
    -1.17
    POSITIVE LOGITS
     you
    0.82
    <bos>
    0.76
     You
    0.75
    you
    0.74
     your
    0.72
    your
    0.71
    You
    0.69
     Your
    0.69
    Your
    0.66
     YOU
    0.60
    Activations Density 0.292%

    No Known Activations