© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 13336
    Prev
    Next
    INDEX
    Explanations

    phrases related to bureaucratic processes or paperwork

    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
    1150
    +0.16
    0.5%
    946
    +0.11
    0.3%
    1553
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1553
    +0.16
    0.04
    1150
    +0.11
    0.02
    946
    +0.11
    0.03
    Negative Logits
    shadowRadius
    -0.63
    };*/
    -0.62
     mourut
    -0.60
     Drapeau
    -0.59
    })*/
    -0.58
    !*\
    -0.57
    setBold
    -0.54
    ImageBackground
    -0.54
     allAfrica
    -0.54
    aarrggbb
    -0.53
    POSITIVE LOGITS
     suscep
    0.90
     apprehen
    0.89
     unspeak
    0.85
     gaily
    0.82
     excru
    0.81
     disagre
    0.79
     horrend
    0.78
     indescri
    0.78
     disreg
    0.78
     scrat
    0.76
    Activations Density 0.258%

    No Known Activations