Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 15154
    Prev
    Next
    INDEX
    Explanations

    verbs related to legal actions and criminal behavior, specifically related to sexual offenses against minors

    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
    +0.26
    0.9%
    1967
    +0.19
    0.6%
    1978
    +0.19
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1967
    +0.26
    0.03
    453
    +0.19
    0.03
    1987
    +0.19
    0.02
    Negative Logits
     shenan
    -1.95
     reluct
    -1.87
     maneu
    -1.87
     intersper
    -1.86
     impra
    -1.81
     milf
    -1.81
     encomp
    -1.80
     increa
    -1.74
     scrat
    -1.74
     snoopy
    -1.72
    POSITIVE LOGITS
    databind
    0.68
    ómicos
    0.60
    UTF
    0.56
    rália
    0.55
    izzera
    0.55
     
    0.54
    Pageable
    0.54
    ActionEvent
    0.54
    מבר
    0.54
    ModelAttribute
    0.54
    Activations Density 0.127%

    No Known Activations