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. 1519
    Prev
    Next
    INDEX
    Explanations

    mentions of various locations and venues, potentially related to local attractions or events

    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
    382
    +0.23
    0.8%
    184
    +0.19
    0.7%
    1535
    +0.19
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.23
    0.05
    184
    +0.19
    0.02
    1535
    +0.19
    0.03
    Negative Logits
    igenous
    -0.86
     ristor
    -0.82
    izational
    -0.82
     azule
    -0.81
     venuto
    -0.78
     dolom
    -0.77
     torner
    -0.76
    ropriate
    -0.76
     andato
    -0.75
     succede
    -0.74
    POSITIVE LOGITS
    Ekster
    0.87
     exemplaire
    0.86
     équipement
    0.81
     éclairage
    0.81
     Again
    0.80
     karton
    0.80
     However
    0.79
     vété
    0.78
    Etimo
    0.77
     Unlike
    0.77
    Activations Density 0.073%

    No Known Activations