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. 15381
    Prev
    Next
    INDEX
    Explanations

    mentions of financial transactions and corruption

    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
    1842
    +0.29
    1.0%
    752
    +0.21
    0.7%
    1967
    +0.20
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.29
    0.08
    16
    +0.21
    0.08
    1967
    +0.20
    0.05
    Negative Logits
    Và
    -0.67
    ("="
    -0.66
    ITERIA
    -0.63
    ('=
    -0.60
    )$/,
    -0.59
     يتيمه
    -0.59
    )>=
    -0.59
    Đây
    -0.57
    Còn
    -0.57
    Kết
    -0.57
    POSITIVE LOGITS
     déplo
    1.20
     fameux
    1.17
     vété
    1.15
     Juf
    1.14
     désert
    1.10
     tournant
    1.09
     redé
    1.08
     hcm
    1.08
     Sén
    1.07
     carrefour
    1.07
    Activations Density 0.487%

    No Known Activations