© 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. 13670
    Prev
    Next
    INDEX
    Explanations

    the repeated occurrence of the word "newly"

    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
    410
    +0.13
    0.7%
    130
    +0.13
    0.7%
    206
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    206
    +0.13
    0.01
    424
    +0.13
    0.01
    29
    +0.12
    0.01
    Negative Logits
    iencies
    -2.21
    uously
    -1.73
    esides
    -1.73
    iber
    -1.56
    rapeut
    -1.56
    osit
    -1.55
    ivalent
    -1.52
    ivalence
    -1.50
    oso
    -1.50
    ility
    -1.49
    POSITIVE LOGITS
    ya
    1.75
     extinct
    1.65
    wed
    1.65
     risen
    1.61
     launched
    1.51
    fashioned
    1.51
    born
    1.51
    market
    1.47
     unemployed
    1.46
    grown
    1.46
    Activations Density 0.061%

    No Known Activations