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. 8323
    Prev
    Next
    INDEX
    Explanations

    names of people with a particular emphasis on a specific name which is likely the most relevant person

    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
    227
    +0.15
    0.5%
    1343
    +0.14
    0.4%
    1150
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.15
    0.07
    227
    +0.14
    0.06
    1097
    +0.13
    0.06
    Negative Logits
    capulco
    -0.65
    //}
    
    -0.60
    //...
    -0.59
     carina
    -0.59
     noblesse
    -0.58
     companyId
    -0.55
    ///**
    -0.55
     assiste
    -0.55
    jillo
    -0.55
     superiori
    -0.54
    POSITIVE LOGITS
    OGND
    0.71
    Ekster
    0.58
    Cyfarwyddwr
    0.55
     avancée
    0.54
     shenan
    0.53
     Stretcher
    0.52
     vecteur
    0.51
    ategorien
    0.51
     Ornaments
    0.51
     volon
    0.50
    Activations Density 0.175%

    No Known Activations