© 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. 11082
    Prev
    Next
    INDEX
    Explanations

    phrases related to policy and legislative changes regarding labor, trade unions, and government 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
    1577
    +0.25
    0.8%
    1842
    +0.18
    0.6%
    856
    +0.17
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1842
    +0.25
    0.11
    1819
    +0.18
    0.11
    1438
    +0.17
    0.07
    Negative Logits
     reluct
    -1.61
     disagre
    -1.52
     desir
    -1.49
     emphat
    -1.49
     volunte
    -1.49
     inev
    -1.47
     fuf
    -1.46
     unlaw
    -1.44
     encomp
    -1.44
     fta
    -1.43
    POSITIVE LOGITS
    .
    0.84
    }$.
    0.77
    $.
    0.76
    }.
    0.74
    ().
    0.74
    ).
    0.73
    。
    0.72
    ↵↵↵↵
    0.72
    `.
    0.71
    ].
    0.70
    Activations Density 1.303%

    No Known Activations