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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 11850
    Prev
    Next
    INDEX
    Explanations

    elements related to communication and identification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/2-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    369
    +0.20
    1.2%
    263
    +0.20
    1.1%
    436
    +0.16
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    263
    +0.20
    0.09
    369
    +0.20
    0.03
    436
    +0.16
    0.06
    Negative Logits
    ĥ½
    -2.69
    £
    -2.39
    ľĵ
    -2.28
    ¿½
    -2.27
                
    -2.21
                                           
    -2.21
    č↵       
    -2.21
                                                                           
    -2.21
                                  
    -2.21
                                                         
    -2.21
    POSITIVE LOGITS
    zilla
    1.60
     ceiling
    1.46
     standards
    1.46
     institution
    1.41
    gaard
    1.32
     physicist
    1.29
     filmmaker
    1.27
     lens
    1.27
     means
    1.26
    ferroni
    1.25
    Activations Density 1.126%

    No Known Activations