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. 682
    Prev
    Next
    INDEX
    Explanations

    concerns about security, government actions, and decision-making

    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
    453
    +0.14
    0.4%
    1177
    +0.11
    0.3%
    1978
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.14
    0.08
    1415
    +0.11
    0.03
    299
    +0.10
    0.06
    Negative Logits
     trouva
    -1.23
     tremb
    -1.19
     soigne
    -1.18
     exé
    -1.14
     milano
    -1.13
     bourgeo
    -1.12
     napoli
    -1.09
     peppa
    -1.09
     incess
    -1.09
     dises
    -1.08
    POSITIVE LOGITS
     use
    0.79
     using
    0.67
     deliberately
    0.66
     intentionally
    0.65
     doing
    0.63
     successfully
    0.60
     uses
    0.60
     manually
    0.59
     knowingly
    0.59
     voluntarily
    0.59
    Activations Density 0.712%

    No Known Activations