© 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. 5234
    Prev
    Next
    INDEX
    Explanations

    references to military operations, attacks, and sequels in the text

    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
    764
    +0.10
    0.3%
    1870
    +0.09
    0.3%
    1984
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    74
    +0.10
    0.05
    764
    +0.09
    0.05
    1867
    +0.08
    0.04
    Negative Logits
     squa
    -1.29
     aen
    -1.27
     fta
    -1.26
     „,
    -1.22
     embra
    -1.20
     effe
    -1.19
     mef
    -1.18
     contex
    -1.17
     Intere
    -1.17
     secon
    -1.16
    POSITIVE LOGITS
     would
    0.69
     wouldn
    0.64
     like
    0.62
     involving
    0.61
     based
    0.59
     could
    0.58
    like
    0.58
     beyond
    0.58
     similar
    0.57
    would
    0.57
    Activations Density 0.540%

    No Known Activations