© 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 EvalsExportsinterp-engineNEWAPI 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. 5102
    Prev
    Next
    INDEX
    Explanations

    references to legal compliance

    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
    1778
    +0.13
    0.5%
    120
    +0.11
    0.4%
    893
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1778
    +0.13
    0.02
    188
    +0.11
    0.02
    1379
    +0.11
    0.02
    Negative Logits
     unlaw
    -0.83
     impractica
    -0.83
     embra
    -0.82
     prouve
    -0.80
     indestru
    -0.78
     revan
    -0.75
     Mlle
    -0.74
     soutient
    -0.73
     reconnaît
    -0.72
     prendra
    -0.72
    POSITIVE LOGITS
     compliance
    1.32
    compliance
    1.23
     Compliance
    1.20
     comply
    1.17
    Compliance
    1.10
     compliant
    1.08
    compliant
    1.07
    PLIANCE
    0.98
     complying
    0.98
     complies
    0.95
    Activations Density 0.082%

    No Known Activations