© 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. 13405
    Prev
    Next
    INDEX
    Explanations

    text related to trade agreements and tariff regulations

    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
    1967
    +0.29
    1.0%
    1108
    +0.23
    0.8%
    674
    +0.21
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1967
    +0.29
    0.08
    453
    +0.23
    0.07
    1108
    +0.21
    0.07
    Negative Logits
     apprehen
    -1.63
     encomp
    -1.59
     intersper
    -1.58
     maneu
    -1.56
     unspeak
    -1.54
     affor
    -1.53
     disagre
    -1.53
     reluct
    -1.53
     gaily
    -1.52
     increa
    -1.49
    POSITIVE LOGITS
    <bos>
    0.83
    ⇑
    0.57
    UIControlState
    0.56
     himo
    0.56
    ˋ
    0.54
    цездатний
    0.54
    DoubleQuotes
    0.53
    kuuta
    0.53
    ectoria
    0.51
     FetchType
    0.51
    Activations Density 0.807%

    No Known Activations