© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 28207
    Prev
    Next
    INDEX
    Explanations

    elements and structures related to programming and data representation

    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
    141
    +0.17
    1.0%
    270
    +0.16
    0.9%
    302
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    13
    +0.17
    0.08
    270
    +0.16
    0.11
    185
    +0.16
    0.06
    Negative Logits
    amine
    -1.59
    opter
    -1.47
     (>
    -1.45
    .',
    -1.39
    cast
    -1.39
     right
    -1.37
     themselves
    -1.35
     ourselves
    -1.34
    ."""
    -1.34
    ifen
    -1.34
    POSITIVE LOGITS
     0000000000000000000000000000000000
    1.93
    ruptcy
    1.70
    uary
    1.57
    greg
    1.53
     births
    1.49
    @
    1.48
    ^](#
    1.44
    uelle
    1.44
    à¯į
    1.43
     verd
    1.39
    Activations Density 4.450%

    No Known Activations