© 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. 5330
    Prev
    Next
    INDEX
    Explanations

    phrases related to social commentary and political thought

    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
    1108
    +0.10
    0.3%
    1343
    +0.09
    0.3%
    184
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1524
    +0.10
    0.05
    227
    +0.09
    0.06
    1965
    +0.09
    0.04
    Negative Logits
     reluct
    -2.08
     depic
    -1.92
     accla
    -1.91
     indestru
    -1.90
     encomp
    -1.89
     shenan
    -1.86
     philanth
    -1.85
     maneu
    -1.85
     impra
    -1.80
     increa
    -1.80
    POSITIVE LOGITS
    <bos>
    0.80
     whose
    0.74
     المعرف
    0.70
    Hochspringen
    0.69
     where
    0.67
    Obrázky
    0.67
     with
    0.67
     which
    0.66
    fillType
    0.66
     odkazy
    0.66
    Activations Density 0.533%

    No Known Activations