© 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. 31295
    Prev
    Next
    INDEX
    Explanations

    large numerical data points, particularly in the context of statistics or financial metrics

    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
    286
    +0.15
    0.8%
    21
    +0.13
    0.7%
    203
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    286
    +0.15
    0.05
    342
    +0.13
    0.04
    452
    +0.11
    0.04
    Negative Logits
    rov
    -1.46
     Âł
    -1.44
    versible
    -1.41
    utting
    -1.40
    ogue
    -1.38
    decoration
    -1.37
    APTER
    -1.36
     ')
    -1.34
    axial
    -1.34
     mate
    -1.34
    POSITIVE LOGITS
     miles
    1.85
     dollar
    1.74
    los
    1.68
     jobs
    1.67
     feet
    1.65
     personas
    1.65
    %"
    1.64
     lbs
    1.60
     dots
    1.59
     annually
    1.59
    Activations Density 0.173%

    No Known Activations