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. 15759
    Prev
    Next
    INDEX
    Explanations

    information related to regulations, costs, and studies, particularly regarding governmental actions and financial impacts

    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
    198
    +0.13
    0.4%
    1445
    +0.12
    0.4%
    1253
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.13
    0.05
    198
    +0.12
    0.04
    359
    +0.11
    0.04
    Negative Logits
     inkább
    -0.56
    !!!!
    -0.52
     semmi
    -0.51
     tudom
    -0.51
     ovate
    -0.50
     Вікіпе
    -0.49
     lehe
    -0.49
     !
    -0.48
     hogyan
    -0.48
     siker
    -0.47
    POSITIVE LOGITS
     simplif
    1.09
     allarg
    1.04
     rispond
    1.03
     répon
    1.02
     nece
    0.99
     fep
    0.97
     kasa
    0.97
     quoique
    0.96
     estimat
    0.95
     umo
    0.95
    Activations Density 0.336%

    No Known Activations