© 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. 28158
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to convenience

    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
    156
    +0.17
    1.0%
    148
    +0.17
    1.0%
    231
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    231
    +0.17
    0.03
    114
    +0.17
    0.03
    148
    +0.14
    0.02
    Negative Logits
    zen
    -1.53
    isher
    -1.53
    UC
    -1.42
    chal
    -1.39
    uthan
    -1.35
    ishes
    -1.34
     greatest
    -1.34
    ishi
    -1.31
    atro
    -1.28
    sen
    -1.28
    POSITIVE LOGITS
    noreply
    1.91
    ibly
    1.81
    ously
    1.81
    µ
    1.78
    "}](#
    1.54
    uing
    1.52
    ĻĤ
    1.51
     means
    1.50
    edia
    1.49
    nier
    1.46
    Activations Density 0.114%

    No Known Activations