© 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. 10784
    Prev
    Next
    INDEX
    Explanations

    phrases that express strong personal opinions or preferences

    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
    1919
    +0.19
    0.6%
    381
    +0.16
    0.5%
    906
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.19
    0.10
    1415
    +0.16
    0.06
    805
    +0.12
    0.07
    Negative Logits
     sacerd
    -0.93
     fosfor
    -0.91
     virtù
    -0.91
     gubern
    -0.89
     masaj
    -0.89
     parlamento
    -0.89
     venuto
    -0.88
     affitto
    -0.88
     monaster
    -0.86
     competen
    -0.86
    POSITIVE LOGITS
     disagre
    1.07
     apprehen
    1.04
     reluct
    1.03
     appreci
    0.99
     impra
    0.98
     accla
    0.95
     encomp
    0.92
     unsus
    0.90
     ineffec
    0.89
     shenan
    0.88
    Activations Density 0.247%

    No Known Activations