© 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. 5839
    Prev
    Next
    INDEX
    Explanations

    political figures and events

    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
    604
    +0.15
    0.4%
    1842
    +0.11
    0.3%
    964
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    402
    +0.15
    0.06
    344
    +0.11
    0.04
    1904
    +0.11
    0.05
    Negative Logits
    <bos>
    -1.24
     scrat
    -1.01
     shenan
    -0.94
     contribut
    -0.93
     upvoted
    -0.91
     resear
    -0.88
     sophistic
    -0.87
     disreg
    -0.87
     wip
    -0.85
     boop
    -0.85
    POSITIVE LOGITS
     virtù
    0.61
     regime
    0.61
     peito
    0.58
    #+#
    0.57
    ніципа
    0.57
    AfterClass
    0.56
    devším
    0.56
     kasarigan
    0.55
    DataURL
    0.55
     controlada
    0.55
    Activations Density 0.703%

    No Known Activations