© 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. 31691
    Prev
    Next
    INDEX
    Explanations

    references to 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
    156
    +0.27
    1.7%
    17
    +0.17
    1.0%
    397
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.27
    0.01
    379
    +0.17
    0.08
    397
    +0.15
    0.06
    Negative Logits
    ĥ
    -3.46
    ĥ½
    -3.18
    ĵ
    -3.14
    ·¸
    -3.11
    ´
    -3.10
    Ĥ¬
    -3.08
    ľ
    -3.04
    ij
    -2.97
    »¿
    -2.88
    ŀ
    -2.78
    POSITIVE LOGITS
     itself
    1.88
     below
    1.66
     isn
    1.60
     above
    1.56
    strings
    1.56
    boards
    1.51
    adder
    1.43
    code
    1.40
    osphere
    1.40
     doesn
    1.38
    Activations Density 0.674%

    No Known Activations