© 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. 1-RES-SM
    11. 24916
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    +0.38
    2.2%
    111
    +0.16
    1.0%
    136
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.38
    0.06
    156
    +0.16
    0.04
    271
    +0.12
    0.02
    Negative Logits
     tomorrow
    -1.66
    Override
    -1.55
     last
    -1.43
     next
    -1.42
     Next
    -1.34
     anytime
    -1.33
    eeee
    -1.28
    dates
    -1.25
     candidates
    -1.23
     Intel
    -1.23
    POSITIVE LOGITS
    ateral
    2.05
    ^](#
    1.82
    axon
    1.68
    ublin
    1.63
    apore
    1.60
    lotte
    1.54
    orentz
    1.50
    ourses
    1.46
    ibraries
    1.45
    CTX
    1.45
    Activations Density 0.108%

    No Known Activations