© 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. 13171
    Prev
    Next
    INDEX
    Explanations

    terms related to conditions and statuses in technical and legal 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
    153
    +0.22
    1.3%
    419
    +0.17
    1.0%
    369
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    153
    +0.22
    0.09
    210
    +0.17
    0.04
    13
    +0.15
    0.07
    Negative Logits
     dealer
    -1.39
     indebted
    -1.38
     candidate
    -1.32
    eric
    -1.30
     toast
    -1.27
    ionic
    -1.25
    iaz
    -1.23
     greenhouse
    -1.22
    antine
    -1.21
     dealership
    -1.20
    POSITIVE LOGITS
     ")
    1.61
    \])]{}
    1.60
    '):
    1.57
    ”),
    1.55
    >)
    1.55
    "),
    1.55
    infty
    1.54
    ”)
    1.54
    ")
    1.48
     itself
    1.42
    Activations Density 3.530%

    No Known Activations