© 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. 5548
    Prev
    Next
    INDEX
    Explanations

    words related to legal actions and political 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
    1842
    +0.19
    0.6%
    198
    +0.14
    0.4%
    856
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1842
    +0.19
    0.07
    939
    +0.14
    0.07
    81
    +0.14
    0.03
    Negative Logits
    <bos>
    -1.49
    спользова
    -0.52
     in
    -0.49
    .
    -0.48
     with
    -0.47
     even
    -0.47
     Dispenser
    -0.46
     Cleanser
    -0.46
     accordingly
    -0.45
     TECHNIQUE
    -0.45
    POSITIVE LOGITS
     soggior
    1.13
     saar
    1.09
     ristor
    1.04
     Jä
    1.02
     bandung
    1.01
     gend
    0.99
     alkoh
    0.99
     circon
    0.97
     eccell
    0.97
     cioc
    0.95
    Activations Density 0.817%

    No Known Activations