© 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. 32074
    Prev
    Next
    INDEX
    Explanations

    information related to service details, pricing, and accommodation options

    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
    369
    +0.19
    1.1%
    150
    +0.14
    0.8%
    410
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    369
    +0.19
    0.07
    410
    +0.14
    0.13
    150
    +0.14
    0.09
    Negative Logits
     {};
    -1.50
     coli
    -1.45
    ↵
    -1.44
    catalina
    -1.44
    exports
    -1.37
    amsfonts
    -1.36
    licenses
    -1.35
    MODULE
    -1.35
    ↵
    -1.34
     sense
    -1.33
    POSITIVE LOGITS
    Į
    2.23
    ¬
    2.22
    ±
    2.19
    Ŀ
    2.14
    ij
    2.13
    ´
    2.08
    ¹
    2.06
    º
    2.01
    ¶
    2.00
    ¿
    1.99
    Activations Density 1.278%

    No Known Activations