© 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. 25598
    Prev
    Next
    INDEX
    Explanations

    mentions of academies or educational institutions

    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
    156
    +0.18
    1.1%
    507
    +0.14
    0.8%
    106
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    451
    +0.18
    0.01
    507
    +0.14
    0.01
    106
    +0.12
    0.02
    Negative Logits
    amyl
    -1.60
    enant
    -1.55
    apine
    -1.52
    othes
    -1.51
    ox
    -1.48
     contag
    -1.46
    appropri
    -1.46
    andem
    -1.45
     aloud
    -1.44
     nature
    -1.43
    POSITIVE LOGITS
     Awards
    2.35
    ĭ
    2.04
    holders
    2.03
    holder
    2.02
     Award
    2.00
    »¿
    1.92
    ground
    1.86
    àµį
    1.83
    à¯į
    1.82
    ction
    1.78
    Activations Density 0.083%

    No Known Activations