© 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. 4-RES-SM
    11. 10060
    Prev
    Next
    INDEX
    Explanations

    nouns and locations related to events and statistics

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    281
    +0.11
    0.6%
    299
    +0.11
    0.6%
    310
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.11
    0.03
    21
    +0.11
    0.00
    216
    +0.11
    0.05
    Negative Logits
    ox
    -1.57
    genic
    -1.55
    OX
    -1.45
    ung
    -1.44
    tex
    -1.42
    xl
    -1.41
     âĨĴ
    -1.41
     ox
    -1.41
     foot
    -1.39
    ledge
    -1.38
    POSITIVE LOGITS
     Mar
    3.65
     Apr
    3.21
     Jan
    3.02
     Dec
    3.00
    Mar
    2.96
     Jul
    2.92
     Nov
    2.91
     Jun
    2.90
     Feb
    2.81
     Sep
    2.78
    Activations Density 0.858%

    No Known Activations