Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 14061
    Prev
    Next
    INDEX
    Explanations

    references to locations and events related to hospitality or tourism

    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
    690
    +0.09
    0.2%
    113
    +0.07
    0.2%
    562
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.09
    0.05
    480
    +0.07
    0.03
    104
    +0.07
    0.02
    Negative Logits
     Darío
    -1.06
     vito
    -1.06
     Áng
    -1.05
     Borja
    -1.02
     Sinal
    -1.01
     Mónica
    -0.97
     Perci
    -0.97
     Valentín
    -0.97
     inappro
    -0.95
     Keny
    -0.95
    POSITIVE LOGITS
     becomes
    0.87
    becomes
    0.79
     become
    0.75
    become
    0.65
     suddenly
    0.56
     switches
    0.54
     switch
    0.54
     transforms
    0.54
     становится
    0.51
    ValueStyle
    0.50
    Activations Density 0.427%

    No Known Activations