© 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 EvalsExportsAPI 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. 10247
    Prev
    Next
    INDEX
    Explanations

    the usage of the "os" library and related system paths in programming code

    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
    +0.18
    1.0%
    369
    +0.16
    0.9%
    446
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    446
    +0.18
    0.02
    369
    +0.16
    0.01
    260
    +0.15
    0.02
    Negative Logits
    uity
    -1.71
    orget
    -1.66
     conjugation
    -1.61
     preponderance
    -1.52
     sync
    -1.51
    dagger
    -1.49
    uation
    -1.48
    ){#
    -1.45
    ishing
    -1.44
     median
    -1.42
    POSITIVE LOGITS
    PECT
    1.76
    borne
    1.72
    Īĺ
    1.58
    sein
    1.57
    pere
    1.52
    ullivan
    1.51
    so
    1.51
    PER
    1.50
    IL
    1.49
    Ľ
    1.45
    Activations Density 0.118%

    No Known Activations