© 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. 31783
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to coding or programming 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
    507
    +0.15
    0.8%
    12
    +0.13
    0.7%
    156
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    142
    +0.15
    0.14
    407
    +0.13
    0.12
    457
    +0.13
    0.10
    Negative Logits
    ¡
    -1.84
    ±
    -1.77
    ¿½
    -1.74
    ij
    -1.70
    ĻĤ
    -1.66
    Ĭ
    -1.62
    ©
    -1.61
    §
    -1.60
    ¾
    -1.58
    Ń
    -1.57
    POSITIVE LOGITS
    Inflater
    1.61
    Bounds
    1.59
     lately
    1.51
    Swift
    1.44
    iterator
    1.40
     won
    1.38
    gap
    1.37
    tochrome
    1.36
    osition
    1.35
     wave
    1.35
    Activations Density 6.005%

    No Known Activations