© 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. 13870
    Prev
    Next
    INDEX
    Explanations

    programming constructs and data structures

    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
    198
    +0.12
    0.7%
    346
    +0.11
    0.6%
    401
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    74
    +0.12
    0.02
    360
    +0.11
    0.02
    101
    +0.11
    0.02
    Negative Logits
    Career
    -1.79
    breviations
    -1.76
    illin
    -1.68
    oa
    -1.56
    og
    -1.54
    edin
    -1.51
    wards
    -1.50
    ably
    -1.48
    Funding
    -1.47
    elia
    -1.44
    POSITIVE LOGITS
    pherd
    1.57
    limits
    1.54
     melting
    1.46
    arshal
    1.45
     sciences
    1.44
     breathe
    1.43
    cout
    1.41
    maker
    1.41
    erver
    1.40
     anyway
    1.38
    Activations Density 0.183%

    No Known Activations