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. 15927
    Prev
    Next
    INDEX
    Explanations

    locations and events related to Miami

    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
    1624
    +0.16
    0.6%
    200
    +0.14
    0.5%
    1141
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1624
    +0.16
    0.03
    200
    +0.14
    0.02
    1141
    +0.12
    0.02
    Negative Logits
    Vielleicht
    -0.66
    Może
    -0.64
     disambiguazione
    -0.64
    GARET
    -0.61
    Natürlich
    -0.56
     plancha
    -0.55
     palab
    -0.54
    Demografía
    -0.53
     Normdatei
    -0.53
     ettei
    -0.52
    POSITIVE LOGITS
     Miami
    1.41
    Miami
    1.30
    miami
    1.06
     miami
    0.97
     Oester
    0.89
     Dade
    0.88
     Schrö
    0.80
     Ueb
    0.76
     Mayr
    0.75
     flé
    0.75
    Activations Density 0.052%

    No Known Activations