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. 2830
    Prev
    Next
    INDEX
    Explanations

    references to medical conditions or physical injuries

    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
    196
    +0.14
    0.5%
    1472
    +0.12
    0.5%
    468
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    196
    +0.14
    0.03
    468
    +0.12
    0.03
    1363
    +0.12
    0.03
    Negative Logits
     reluct
    -0.92
     suscep
    -0.85
     disreg
    -0.83
     erad
    -0.82
     increa
    -0.79
     nicolas
    -0.78
     inconce
    -0.77
     volunte
    -0.76
     affor
    -0.76
     maneu
    -0.76
    POSITIVE LOGITS
     injury
    1.30
     injuries
    1.21
     Injury
    1.16
     injured
    1.08
     Injuries
    1.05
    Injury
    1.05
    injury
    1.05
    injured
    0.94
    Injuries
    0.91
     INJ
    0.90
    Activations Density 0.063%

    No Known Activations