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. 1593
    Prev
    Next
    INDEX
    Explanations

    words related to legal and organizational actions

    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
    25
    +0.13
    0.5%
    1870
    +0.13
    0.5%
    1942
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    25
    +0.13
    0.03
    1942
    +0.13
    0.03
    1565
    +0.12
    0.03
    Negative Logits
     Cup
    -0.43
    中学生
    -0.43
    뀌
    -0.43
     Mig
    -0.42
    rim
    -0.42
                            
    -0.41
     ‏
    -0.41
                               
    -0.41
     ri
    -0.41
    地道
    -0.41
    POSITIVE LOGITS
     action
    1.14
     ACTION
    1.08
     Actions
    1.07
     Action
    1.06
    action
    1.04
     actions
    1.02
     affor
    1.02
     strick
    1.00
     scrat
    0.98
     milf
    0.97
    Activations Density 0.076%

    No Known Activations