© 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. 1-RES-SM
    11. 29620
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of "semi" or partial states

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    362
    +0.15
    0.8%
    386
    +0.12
    0.7%
    375
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    404
    +0.15
    0.01
    362
    +0.12
    0.01
    375
    +0.12
    0.01
    Negative Logits
    ¥
    -2.40
    Ķ
    -2.28
    ŀ
    -2.14
    ĨĴ
    -1.95
    Ĥ
    -1.76
    ļ
    -1.69
    ľĵ
    -1.68
    ĵ
    -1.65
    ķ
    -1.63
    Ŀ
    -1.63
    POSITIVE LOGITS
     shop
    1.89
    -,
    1.88
    -
    1.76
    prog
    1.63
    quer
    1.61
    owned
    1.56
    atur
    1.55
    Shop
    1.52
    admin
    1.51
    otic
    1.51
    Activations Density 0.065%

    No Known Activations