© 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. 26459
    Prev
    Next
    INDEX
    Explanations

    terms related to surgical procedures and techniques

    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
    +0.22
    1.2%
    148
    +0.17
    1.0%
    399
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    473
    +0.22
    0.04
    396
    +0.17
    0.03
    4
    +0.12
    0.03
    Negative Logits
    ificantly
    -1.68
    pace
    -1.66
    lessness
    -1.61
    ebook
    -1.51
     affecting
    -1.42
     compete
    -1.41
     grown
    -1.41
     influencing
    -1.40
     consumed
    -1.39
     vanish
    -1.39
    POSITIVE LOGITS
    ĻĤ
    4.36
    £
    4.36
    ³
    4.31
    µ
    4.26
    Ĵ
    4.25
    ¡
    4.24
    ²
    4.17
    ħ
    4.16
    Ħ
    4.14
    ĸ´
    4.08
    Activations Density 0.141%

    No Known Activations