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. 1-RES-SM
    6. 26850
    Prev
    Next
    INDEX
    Explanations

    instances of the word "in" and variations of phrases utilizing "the" and "for"

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    478
    +0.16
    0.9%
    186
    +0.13
    0.7%
    453
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.16
    0.05
    430
    +0.13
    0.03
    478
    +0.12
    0.01
    Negative Logits
    oddsidemargin
    -1.64
    finals
    -1.59
    ieux
    -1.59
    Ļª
    -1.58
    zeit
    -1.53
    water
    -1.49
    enin
    -1.47
    zer
    -1.41
    ielle
    -1.40
    lights
    -1.39
    POSITIVE LOGITS
     ransom
    1.50
    ---|---
    1.45
     various
    1.43
     Alternatively
    1.39
     hire
    1.39
     manufacture
    1.38
    orporated
    1.34
     exped
    1.32
     administrative
    1.31
     practice
    1.31
    Activations Density 0.409%

    No Known Activations