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. 29371
    Prev
    Next
    INDEX
    Explanations

    references to technology-related products and services

    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
    23
    +0.19
    1.1%
    258
    +0.18
    1.0%
    321
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.19
    0.17
    321
    +0.18
    0.11
    23
    +0.15
    0.14
    Negative Logits
    "}](#
    -2.00
     himself
    -1.87
     quarters
    -1.61
     unpublished
    -1.60
    ius
    -1.60
    ural
    -1.56
     physicist
    -1.53
    ème
    -1.51
    "].
    -1.50
     bench
    -1.50
    POSITIVE LOGITS
    č↵č↵ 
    1.76
    Common
    1.68
    #
    1.68
    FORE
    1.61
     [â̦]
    1.55
     Their
    1.54
    COM
    1.53
     respectively
    1.53
     Additionally
    1.53
    ####
    1.52
    Activations Density 1.136%

    No Known Activations