© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 12121
    Prev
    Next
    INDEX
    Explanations

    words related to legal actions and criminal behavior

    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
    674
    +0.10
    0.3%
    1290
    +0.07
    0.2%
    363
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1415
    +0.10
    0.03
    1919
    +0.07
    0.04
    1897
    +0.07
    0.03
    Negative Logits
     hcm
    -0.94
     fta
    -0.92
     fte
    -0.86
     ftu
    -0.85
     Majest
    -0.83
     Fasc
    -0.82
     fays
    -0.82
     Lég
    -0.81
     ··
    -0.79
     thut
    -0.79
    POSITIVE LOGITS
     gladly
    0.77
     WOULD
    0.58
     would
    0.57
    would
    0.57
     wouldn
    0.55
    testify
    0.55
    ypeł
    0.54
    Cyfeiriadau
    0.54
    prefer
    0.54
    Nichts
    0.54
    Activations Density 0.296%

    No Known Activations