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. 26829
    Prev
    Next
    INDEX
    Explanations

    the use of the preposition "to" in various contexts

    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
    44
    +0.14
    0.8%
    505
    +0.13
    0.7%
    215
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.14
    0.07
    505
    +0.13
    0.03
    411
    +0.12
    0.03
    Negative Logits
    giving
    -1.50
    iator
    -1.44
     sentiment
    -1.43
    together
    -1.40
    strap
    -1.40
    craft
    -1.34
    fire
    -1.31
    azine
    -1.30
    ---|
    -1.29
    stan
    -1.28
    POSITIVE LOGITS
    atinib
    1.63
     '';
    1.58
     "";
    1.52
    ves
    1.46
    ARRANT
    1.44
     regret
    1.42
    area
    1.41
     Âĵ
    1.39
     forfe
    1.39
     repeat
    1.39
    Activations Density 0.606%

    No Known Activations