© 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. 27099
    Prev
    Next
    INDEX
    Explanations

    the word "as" used in various contexts

    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
    502
    +0.16
    0.9%
    459
    +0.13
    0.7%
    108
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    502
    +0.16
    0.07
    108
    +0.13
    0.05
    459
    +0.12
    0.04
    Negative Logits
     administer
    -1.61
    itude
    -1.60
     sit
    -1.58
    itud
    -1.58
    ieri
    -1.48
    tees
    -1.44
    acks
    -1.43
    ty
    -1.43
    IONS
    -1.41
     weigh
    -1.41
    POSITIVE LOGITS
    ↵
    3.38
    3.38
    <|outofrange|>
    3.38
    č↵
    3.38
     ↵
    3.38
    č↵
    3.38
    ↵
    3.38
    ↵
    3.38
    ↵
    3.38
    ↵
    3.38
    Activations Density 0.144%

    No Known Activations