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. 15018
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal issues and criminal activities

    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
    1343
    +0.18
    0.6%
    184
    +0.17
    0.6%
    674
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.18
    0.03
    324
    +0.17
    0.03
    651
    +0.16
    0.02
    Negative Logits
     mef
    -1.21
     ivi
    -1.18
     glan
    -1.17
     franz
    -1.15
     daf
    -1.13
     dises
    -1.11
     fluo
    -1.10
     „,
    -1.10
     ghe
    -1.09
     dispen
    -1.08
    POSITIVE LOGITS
     itself
    0.64
     сьогодні
    0.56
    собенности
    0.56
    собенно
    0.55
    engagent
    0.53
     nogen
    0.53
    lcccccc
    0.53
    lccccc
    0.50
     alone
    0.49
     themselves
    0.49
    Activations Density 0.283%

    No Known Activations