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. 15068
    Prev
    Next
    INDEX
    Explanations

    financial terms and details related to legal disputes

    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
    184
    +0.25
    0.8%
    1120
    +0.18
    0.6%
    1445
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.25
    0.02
    1965
    +0.18
    0.03
    1553
    +0.15
    0.04
    Negative Logits
     emphat
    -1.25
     inev
    -1.12
     madonna
    -1.10
     milf
    -1.10
     pessi
    -1.09
     embra
    -1.07
     desir
    -1.07
     perfet
    -1.06
     cannes
    -1.06
     marseille
    -1.06
    POSITIVE LOGITS
    GraphicsUnit
    0.56
    ItemBackground
    0.52
     accounting
    0.51
     صوتيه
    0.50
     vanskelig
    0.49
    aarrggbb
    0.49
     funds
    0.48
     fiscal
    0.48
     dårlig
    0.47
    Chham
    0.47
    Activations Density 0.145%

    No Known Activations