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. 8296
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "pocket."

    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
    1233
    +0.15
    0.6%
    687
    +0.14
    0.6%
    1926
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1233
    +0.15
    0.02
    1872
    +0.14
    0.02
    687
    +0.12
    0.02
    Negative Logits
     inappro
    -0.78
     disagre
    -0.76
     squa
    -0.76
     unden
    -0.74
     sii
    -0.72
     wien
    -0.70
     desir
    -0.70
     emphat
    -0.70
     weber
    -0.68
     edp
    -0.68
    POSITIVE LOGITS
     pocket
    1.58
    pocket
    1.45
     Pocket
    1.42
    Pocket
    1.42
     pockets
    1.35
     Pockets
    1.04
     wallet
    0.93
    wallet
    0.90
     wallets
    0.81
    ポケット
    0.78
    Activations Density 0.098%

    No Known Activations