© 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. 1-RES-SM
    11. 27782
    Prev
    Next
    INDEX
    Explanations

    various forms of suggestions, tips, and concepts for creative inspiration

    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
    156
    +0.26
    1.6%
    365
    +0.15
    0.9%
    10
    +0.14
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.26
    0.06
    111
    +0.15
    0.07
    365
    +0.14
    0.07
    Negative Logits
    ĥ½
    -2.40
    §
    -1.92
    ľĵ
    -1.82
    Ł
    -1.70
    į
    -1.68
    icester
    -1.66
    ĵ
    -1.66
    ¿
    -1.65
     preponderance
    -1.63
    Į
    -1.58
    POSITIVE LOGITS
    nick
    1.69
    urgical
    1.65
    hip
    1.64
    pace
    1.61
     About
    1.61
    manship
    1.51
    flash
    1.49
     targeted
    1.47
    hips
    1.46
    hell
    1.46
    Activations Density 0.441%

    No Known Activations