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. 2954
    Prev
    Next
    INDEX
    Explanations

    sentences expressing feelings related to body image and self-reflection

    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
    906
    +0.12
    0.3%
    658
    +0.10
    0.3%
    1919
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.12
    0.06
    658
    +0.10
    0.07
    1446
    +0.09
    0.03
    Negative Logits
     jorge
    -1.33
     sergio
    -1.27
     shenan
    -1.26
     roberto
    -1.24
     unspeak
    -1.23
     reluct
    -1.23
     prétend
    -1.20
     alberto
    -1.20
     ineffec
    -1.20
     increa
    -1.20
    POSITIVE LOGITS
     excited
    0.79
     feeling
    0.75
     worry
    0.72
     disappointed
    0.70
     worried
    0.70
     feel
    0.68
     feelings
    0.68
     surprised
    0.67
     concern
    0.67
     excitement
    0.67
    Activations Density 0.507%

    No Known Activations