© 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. 6529
    Prev
    Next
    INDEX
    Explanations

    legal terms and lawsuit-related phrases

    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
    227
    +0.11
    0.3%
    1899
    +0.11
    0.3%
    1129
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.11
    0.08
    1899
    +0.11
    0.05
    113
    +0.09
    0.04
    Negative Logits
     broderie
    -0.55
     accepte
    -0.53
     potest
    -0.53
     habet
    -0.52
     triomphe
    -0.51
     péché
    -0.51
    astrous
    -0.51
     rire
    -0.50
     regarde
    -0.50
     bonté
    -0.49
    POSITIVE LOGITS
     Keny
    0.77
     pamph
    0.75
     Abbé
    0.61
     advocacy
    0.60
     Kün
    0.60
     Advocacy
    0.59
     Karang
    0.58
     NGO
    0.58
     Rued
    0.58
     Bartholo
    0.57
    Activations Density 0.434%

    No Known Activations