© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 25771
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the"

    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
    192
    +0.14
    0.8%
    230
    +0.14
    0.8%
    467
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.14
    0.00
    98
    +0.14
    0.00
    164
    +0.12
    0.00
    Negative Logits
    oxid
    -1.68
    ¯
    -1.68
    vez
    -1.65
    ¼
    -1.63
    urope
    -1.58
    ħ
    -1.56
    lung
    -1.55
    ´
    -1.54
    Ĭ
    -1.51
    mium
    -1.47
    POSITIVE LOGITS
    iary
    1.57
     ===
    1.57
    ,—
    1.56
     vote
    1.49
     deduction
    1.46
     â
    1.44
     goal
    1.44
     judgment
    1.43
     ”
    1.43
     ${\
    1.42
    Activations Density 0.000%

    No Known Activations