© 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. 12645
    Prev
    Next
    INDEX
    Explanations

    elements of programming syntax and structure

    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
    231
    +0.16
    0.9%
    161
    +0.16
    0.9%
    358
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    231
    +0.16
    0.12
    6
    +0.16
    0.11
    460
    +0.14
    0.07
    Negative Logits
    ĻĤ
    -4.62
    ¿½
    -3.93
    Ļª
    -3.73
    ľĵ
    -3.72
    Ĺ
    -3.69
    ©
    -3.62
    ²
    -3.61
    Īĺ
    -3.58
    Ĥ¬
    -3.53
    »
    -3.52
    POSITIVE LOGITS
    â
    1.36
    endl
    1.36
     biology
    1.30
    ygon
    1.29
     engineer
    1.29
    uria
    1.29
    findViewById
    1.28
     offended
    1.26
    *~
    1.26
    pless
    1.26
    Activations Density 4.111%

    No Known Activations