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. 428
    Prev
    Next
    INDEX
    Explanations

    instructions for making a specific type of dish, focusing on ingredients and steps

    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
    1511
    +0.15
    0.5%
    964
    +0.14
    0.4%
    876
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1511
    +0.15
    0.02
    1380
    +0.14
    0.01
    163
    +0.10
    0.01
    Negative Logits
     hina
    -0.87
     kule
    -0.83
     Akademi
    -0.81
     kayo
    -0.80
     Seni
    -0.77
     nikah
    -0.76
     nui
    -0.74
     jaya
    -0.72
    <bos>
    -0.72
     Hati
    -0.72
    POSITIVE LOGITS
     sophistic
    1.47
     shenan
    1.46
     reluct
    1.35
     snoopy
    1.30
     unspeak
    1.28
     impractica
    1.28
     unwarran
    1.27
     apprehen
    1.25
     impra
    1.25
     disagre
    1.24
    Activations Density 1.299%

    No Known Activations