© 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. 30791
    Prev
    Next
    INDEX
    Explanations

    references to social engagement and community-related concepts

    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
    156
    +0.16
    0.9%
    362
    +0.12
    0.7%
    309
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    503
    +0.16
    0.03
    18
    +0.12
    0.03
    254
    +0.11
    0.03
    Negative Logits
    Į
    -2.02
    <|outofrange|>
    -1.87
    č↵
    -1.87
    -1.87
    ↵
    -1.87
    ↵
    -1.87
    -1.87
    -1.87
    -1.87
    č↵
    -1.87
    POSITIVE LOGITS
    ization
    2.00
    ized
    1.99
    IZ
    1.96
    ised
    1.96
    ity
    1.95
    izer
    1.92
    izing
    1.75
    IZE
    1.73
    isation
    1.71
    card
    1.70
    Activations Density 0.118%

    No Known Activations