© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 12146
    Prev
    Next
    INDEX
    Explanations

    phrases related to politics and government actions

    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
    874
    +0.13
    0.5%
    871
    +0.13
    0.5%
    1271
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.13
    0.05
    871
    +0.13
    0.03
    1008
    +0.13
    0.03
    Negative Logits
     pajero
    -0.97
     isuzu
    -0.91
     fuj
    -0.87
     hilux
    -0.85
     squa
    -0.84
     skoda
    -0.83
     vios
    -0.83
     nikon
    -0.82
     jbl
    -0.82
     panasonic
    -0.82
    POSITIVE LOGITS
    ]?.
    0.70
    ”.
    0.66
    ".
    0.64
     مشين
    0.63
    ]$.
    0.60
    InjectAttribute
    0.59
    “……”
    0.59
     ***!
    0.58
    __).
    0.57
    ’.
    0.57
    Activations Density 0.146%

    No Known Activations