© 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. 25808
    Prev
    Next
    INDEX
    Explanations

    references to loss or penalties associated with 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
    90
    +0.15
    0.9%
    100
    +0.13
    0.8%
    274
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    90
    +0.15
    0.03
    445
    +0.13
    0.02
    100
    +0.12
    0.02
    Negative Logits
     Parenthood
    -1.65
    herin
    -1.53
    typeof
    -1.52
    uron
    -1.52
     Asst
    -1.49
    usement
    -1.44
    rens
    -1.41
    them
    -1.40
    thems
    -1.39
     malaria
    -1.37
    POSITIVE LOGITS
    ive
    1.89
     zone
    1.86
     mode
    1.80
     compartment
    1.70
    ģ
    1.65
    Ģ
    1.65
     occasion
    1.62
    garten
    1.60
     details
    1.58
    ļ
    1.54
    Activations Density 0.086%

    No Known Activations