© 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. 27630
    Prev
    Next
    INDEX
    Explanations

    the word "inn" in various contexts

    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
    66
    +0.13
    0.7%
    256
    +0.12
    0.7%
    410
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.13
    0.01
    250
    +0.12
    0.02
    317
    +0.11
    0.01
    Negative Logits
     "*
    -1.52
     *)
    -1.49
     insensitive
    -1.47
     <
    -1.46
     coding
    -1.45
    xymatrix
    -1.44
     correctness
    -1.44
     subclass
    -1.44
     minimal
    -1.43
     strongly
    -1.42
    POSITIVE LOGITS
    ovation
    1.97
    bard
    1.78
    ĩ
    1.78
    chez
    1.75
    ifer
    1.70
    emann
    1.64
    kowski
    1.59
    agar
    1.58
    ermost
    1.57
    enue
    1.57
    Activations Density 0.095%

    No Known Activations