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. 640
    Prev
    Next
    INDEX
    Explanations

    references to notable people and their works, such as actors, authors, and their related projects

    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
    227
    +0.20
    0.6%
    1343
    +0.18
    0.5%
    2034
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.20
    0.10
    1842
    +0.18
    0.06
    791
    +0.11
    0.04
    Negative Logits
     rispond
    -1.05
     scopri
    -1.03
     parteci
    -1.03
     dimenti
    -1.02
     purtroppo
    -0.98
     vediamo
    -0.91
     migli
    -0.90
     conosce
    -0.89
     anzi
    -0.88
     interessa
    -0.87
    POSITIVE LOGITS
     unspeak
    1.13
     indescri
    1.03
     vainly
    1.03
     impra
    1.03
     gaily
    1.00
     inconce
    0.96
     apprehen
    0.95
     ineffec
    0.95
     horrend
    0.94
     disagre
    0.92
    Activations Density 0.579%

    No Known Activations