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. 2937
    Prev
    Next
    INDEX
    Explanations

    phrases related to emotional intensity and reactions

    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
    674
    +0.26
    0.8%
    184
    +0.14
    0.4%
    332
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.26
    0.08
    1363
    +0.14
    0.06
    1013
    +0.10
    0.07
    Negative Logits
     increa
    -3.58
     effe
    -3.51
     inev
    -3.50
     fta
    -3.40
     ftu
    -3.39
     impra
    -3.39
     affor
    -3.38
     unden
    -3.37
     wien
    -3.36
     reluct
    -3.34
    POSITIVE LOGITS
    <bos>
    1.40
     BoxFit
    1.01
    GOTREF
    0.97
    .
    0.91
    ClientRect
    0.90
    ↵↵
    0.89
    …
    0.88
    HomeAsUpEnabled
    0.87
     
    0.86
    WithFormat
    0.86
    Activations Density 0.744%

    No Known Activations