© 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. 10267
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "go."

    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
    130
    +0.13
    0.7%
    263
    +0.12
    0.7%
    477
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    272
    +0.13
    0.05
    130
    +0.12
    0.05
    471
    +0.12
    0.03
    Negative Logits
    ŀ
    -2.71
    Ļ
    -2.48
    Į
    -2.40
    »¿
    -2.29
    ĺ
    -2.26
    Ļª
    -2.26
    §
    -2.21
    ij
    -2.19
    ı
    -2.18
    ly
    -2.17
    POSITIVE LOGITS
    vt
    2.02
    bject
    2.00
    bb
    1.97
    hl
    1.89
     crazy
    1.86
     viral
    1.82
     astr
    1.76
    ofs
    1.76
    fund
    1.69
    bs
    1.64
    Activations Density 0.145%

    No Known Activations