© 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. 2-RES-SM
    11. 31024
    Prev
    Next
    INDEX
    Explanations

    terms associated with established systems, organizations, or industries

    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
    198
    +0.15
    0.9%
    231
    +0.13
    0.8%
    246
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.15
    0.12
    29
    +0.13
    0.04
    231
    +0.11
    0.09
    Negative Logits
    iles
    -1.62
    anas
    -1.59
    inus
    -1.50
    oprop
    -1.43
     ash
    -1.41
    uku
    -1.39
     their
    -1.37
    ols
    -1.37
    atives
    -1.36
    ãĤĩ
    -1.36
    POSITIVE LOGITS
    ĻĤ
    2.72
    ¾
    2.72
    2.67
    ↵
    2.67
    2.67
    <|outofrange|>
    2.67
            ↵
    2.67
     ↵
    2.67
     ↵
    2.67
    č↵
    2.67
    Activations Density 1.130%

    No Known Activations