© 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. 14921
    Prev
    Next
    INDEX
    Explanations

    technical specifications related to XML schemas and their versions

    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
    412
    +0.17
    1.0%
    78
    +0.15
    0.9%
    425
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    412
    +0.17
    0.04
    425
    +0.15
    0.03
    353
    +0.12
    0.03
    Negative Logits
    soever
    -2.16
    istically
    -1.74
    antly
    -1.73
    entes
    -1.64
     regard
    -1.57
    icipants
    -1.55
     interested
    -1.54
    cerning
    -1.49
     concerned
    -1.45
     newsletters
    -1.44
    POSITIVE LOGITS
    ubuntu
    1.67
     GHz
    1.65
    GHz
    1.54
    veis
    1.54
     Collaboration
    1.53
     kb
    1.49
     equivalents
    1.49
    pc
    1.48
    cm
    1.48
    eV
    1.43
    Activations Density 0.086%

    No Known Activations