© 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. 13818
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs and 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
    235
    +0.24
    1.4%
    419
    +0.22
    1.3%
    323
    +0.20
    1.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.24
    0.34
    111
    +0.22
    0.29
    71
    +0.20
    0.31
    Negative Logits
    ĩ
    -2.24
    ł
    -2.21
    ĥ½
    -2.19
    ¥
    -2.15
    ¦
    -2.14
    Ł
    -2.08
    ª
    -2.06
    Ī
    -2.02
    ¸
    -2.01
    ĵ
    -1.96
    POSITIVE LOGITS
    cake
    1.44
     arrangements
    1.39
     Miranda
    1.35
    anus
    1.33
    yrus
    1.33
    fork
    1.32
     throne
    1.32
    liver
    1.30
     injections
    1.30
     beans
    1.29
    Activations Density 5.824%

    No Known Activations