© 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. 24973
    Prev
    Next
    INDEX
    Explanations

    the presence of mathematical structures and properties

    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
    478
    +0.19
    1.1%
    100
    +0.13
    0.7%
    176
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    67
    +0.19
    0.03
    175
    +0.13
    0.04
    51
    +0.12
    0.03
    Negative Logits
    ually
    -1.75
    ging
    -1.64
     ?
    -1.63
    urs
    -1.60
     sickness
    -1.54
     mode
    -1.53
    ust
    -1.52
    }}</
    -1.50
    ](
    -1.50
    ual
    -1.47
    POSITIVE LOGITS
    amsbsy
    2.08
    wasysym
    2.00
    onas
    1.80
     fan
    1.54
    ĨĴ
    1.54
    1.52
    1.52
    1.52
    ↵
    1.52
    1.52
    Activations Density 0.112%

    No Known Activations