© 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. 12586
    Prev
    Next
    INDEX
    Explanations

    the concept of lacking something despite expectations

    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
    186
    +0.16
    0.9%
    11
    +0.11
    0.6%
    157
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    11
    +0.16
    0.02
    315
    +0.11
    0.01
    226
    +0.11
    0.02
    Negative Logits
    isations
    -1.64
    isation
    -1.56
    oused
    -1.52
    utors
    -1.49
    izations
    -1.48
    ediatric
    -1.44
    atonin
    -1.42
    istes
    -1.42
    oretic
    -1.38
    ortical
    -1.33
    POSITIVE LOGITS
    krit
    1.30
     égal
    1.28
    enstein
    1.27
    ee
    1.27
    respect
    1.26
     Agreement
    1.25
     logos
    1.21
    degree
    1.21
     Order
    1.18
    zig
    1.17
    Activations Density 0.054%

    No Known Activations