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

    Neuronpedia

    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. 2-RES-SM
    11. 12491
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and operations

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    163
    +0.12
    0.7%
    281
    +0.12
    0.7%
    197
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    251
    +0.12
    0.02
    253
    +0.12
    0.02
    163
    +0.11
    0.02
    Negative Logits
    cursors
    -1.63
    genic
    -1.58
    xymatrix
    -1.55
    ('/
    -1.45
    ')\
    -1.44
    onium
    -1.43
    ![**
    -1.43
    "}**).
    -1.41
    purpose
    -1.39
    .’”
    -1.39
    POSITIVE LOGITS
    annel
    1.59
     Wine
    1.59
    nier
    1.49
     Weinstein
    1.42
     Films
    1.42
     hats
    1.39
     Employees
    1.38
    th
    1.37
     Ware
    1.36
    nell
    1.33
    Activations Density 0.087%

    No Known Activations