© 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. 28937
    Prev
    Next
    INDEX
    Explanations

    words related to chicken dishes or recipes

    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
    +0.17
    0.9%
    111
    +0.13
    0.7%
    55
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.17
    0.15
    156
    +0.13
    0.08
    271
    +0.12
    0.06
    Negative Logits
    InstanceState
    -1.62
    Lists
    -1.61
    Options
    -1.53
    ĸ
    -1.50
    entials
    -1.50
    Dependencies
    -1.48
    eners
    -1.47
    ľ
    -1.47
    ĵ
    -1.42
    ktop
    -1.38
    POSITIVE LOGITS
    ish
    1.68
    akra
    1.66
    andra
    1.62
    arming
    1.58
    thon
    1.57
    oud
    1.53
    ander
    1.50
    allenge
    1.49
     smoked
    1.46
    ^](#
    1.46
    Activations Density 0.266%

    No Known Activations