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. 26764
    Prev
    Next
    INDEX
    Explanations

    the word "actually" and its variations, indicating emphasis or clarification in statements

    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
    23
    +0.21
    1.2%
    257
    +0.15
    0.8%
    365
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.21
    0.08
    156
    +0.15
    0.05
    202
    +0.12
    0.06
    Negative Logits
    ħ
    -2.38
    ģ
    -2.24
    Ĵ
    -2.22
    Ģ
    -2.16
    ĨĴ
    -2.14
    Ĩ
    -2.09
    Ħ
    -2.03
    Ľ
    -2.00
    ¥
    -1.98
    IJ
    -1.95
    POSITIVE LOGITS
     '')
    1.89
     breathing
    1.89
     euthan
    1.65
     existed
    1.59
     flown
    1.56
    doing
    1.52
     vomiting
    1.48
     "")
    1.48
     hurt
    1.46
     finding
    1.45
    Activations Density 0.522%

    No Known Activations