© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 14530
    Prev
    Next
    INDEX
    Explanations

    the word "the" used multiple times 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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    21
    +0.16
    0.9%
    98
    +0.13
    0.7%
    478
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    34
    +0.16
    0.01
    98
    +0.13
    0.01
    371
    +0.12
    0.01
    Negative Logits
    izabeth
    -1.48
    orphic
    -1.46
    ipore
    -1.45
     influ
    -1.41
     exerted
    -1.40
     couples
    -1.40
    esian
    -1.40
     orn
    -1.36
     attracts
    -1.33
    enron
    -1.32
    POSITIVE LOGITS
     "
    1.90
    license
    1.87
     License
    1.85
     "")
    1.84
     "`
    1.81
     "~
    1.76
     "[
    1.74
     "'
    1.73
    License
    1.65
     "!"
    1.65
    Activations Density 0.023%

    No Known Activations