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. 15836
    Prev
    Next
    INDEX
    Explanations

    the word "calm" and related phrases indicating a sense of tranquility or peace

    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
    30
    +0.15
    0.5%
    1557
    +0.11
    0.3%
    1537
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1557
    +0.15
    0.03
    30
    +0.11
    0.03
    1043
    +0.10
    0.03
    Negative Logits
     affor
    -1.13
     increa
    -1.06
     !...
    -1.02
     purcha
    -1.00
     volunte
    -1.00
     indestru
    -0.99
     perciò
    -0.99
     reluct
    -0.97
     encomp
    -0.97
     impra
    -0.97
    POSITIVE LOGITS
     calm
    1.30
    calm
    1.05
    Calm
    1.03
     Calm
    0.99
     calming
    0.96
     calmed
    0.90
     calmness
    0.90
     calmly
    0.88
     calms
    0.78
     calmer
    0.77
    Activations Density 0.162%

    No Known Activations