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. 8410
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal documents or policies

    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
    50
    +0.26
    0.9%
    1741
    +0.21
    0.7%
    1967
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.26
    0.10
    50
    +0.21
    0.07
    1967
    +0.17
    0.07
    Negative Logits
     kasarigan
    -0.91
     pensieri
    -0.91
     sentimenti
    -0.85
     parut
    -0.83
     sogni
    -0.78
     florales
    -0.76
     kompati
    -0.76
    verifyException
    -0.76
     felicità
    -0.74
     commenti
    -0.71
    POSITIVE LOGITS
     same
    0.66
     Varies
    0.63
     Facile
    0.62
    Mechanisms
    0.61
     fanci
    0.61
     impractica
    0.60
     Applicability
    0.60
     dreaded
    0.58
     aforementioned
    0.57
     Defective
    0.56
    Activations Density 0.510%

    No Known Activations