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. 703
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations, particularly Las Vegas

    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
    1178
    +0.15
    0.6%
    1637
    +0.12
    0.5%
    1335
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1178
    +0.15
    0.04
    1335
    +0.12
    0.03
    1637
    +0.11
    0.03
    Negative Logits
    strona
    -0.57
    aucun
    -0.50
    ɵɵelementEnd
    -0.49
    agaimana
    -0.47
    Aún
    -0.47
    ৷
    -0.47
    Jako
    -0.46
     Tampoco
    -0.46
     Ellos
    -0.46
     Aún
    -0.45
    POSITIVE LOGITS
     Vegas
    1.34
    Vegas
    1.20
     VEGAS
    1.13
    vegas
    1.11
     Las
    1.10
     vegas
    1.09
     Nevada
    1.07
    Nevada
    0.94
    Las
    0.93
     nevada
    0.78
    Activations Density 0.090%

    No Known Activations