© 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. 1-RES-SM
    11. 24191
    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
    23
    +0.31
    1.9%
    478
    +0.16
    1.0%
    10
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.31
    0.11
    164
    +0.16
    0.09
    507
    +0.15
    0.06
    Negative Logits
    illac
    -1.79
    ale
    -1.79
    ello
    -1.78
    "}\].
    -1.76
    ondo
    -1.70
    etto
    -1.70
    ôt
    -1.68
    \]\].
    -1.66
    elta
    -1.65
    ificate
    -1.65
    POSITIVE LOGITS
    ·
    2.44
     entire
    2.35
     latter
    2.30
    ľ
    2.29
    ↵↵
    2.28
    ↵
    2.28
    ↵↵
    2.28
    ↵
    2.28
            ↵
    2.28
     ↵
    2.28
    Activations Density 1.319%

    No Known Activations