© 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. 13042
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and identifiers

    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
    489
    +0.13
    0.7%
    203
    +0.12
    0.7%
    21
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    74
    +0.13
    0.05
    295
    +0.12
    0.07
    203
    +0.12
    0.06
    Negative Logits
    endants
    -1.75
    endent
    -1.74
    (**
    -1.63
    plasia
    -1.60
    inctions
    -1.59
    ocations
    -1.56
    ($
    -1.53
    ittings
    -1.50
    ![**
    -1.50
    ('/
    -1.48
    POSITIVE LOGITS
    Ĥ
    4.20
    ¾
    4.19
    ¹
    4.12
    ³
    4.12
    º
    4.12
    ĸ´
    3.98
    Ĥ¬
    3.97
    ¸
    3.96
    ľ
    3.93
    °
    3.90
    Activations Density 0.468%

    No Known Activations