© 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. 31841
    Prev
    Next
    INDEX
    Explanations

    expressions related to programming or scripting commands

    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
    12
    +0.19
    1.1%
    240
    +0.12
    0.7%
    442
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    12
    +0.19
    0.16
    7
    +0.12
    -0.01
    338
    +0.11
    0.03
    Negative Logits
    »¿
    -2.05
    Ī
    -1.95
    ¹
    -1.92
    ľ
    -1.89
    ĩ
    -1.89
    Ĩ
    -1.88
    ¶
    -1.88
    ĺ
    -1.85
    §
    -1.81
    ´
    -1.80
    POSITIVE LOGITS
    ffer
    1.80
    ively
    1.57
    anus
    1.46
    Äij
    1.42
     lasted
    1.39
     slept
    1.37
    icates
    1.36
    obbsee
    1.33
    antly
    1.33
    atan
    1.29
    Activations Density 6.496%

    No Known Activations