© 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. 28116
    Prev
    Next
    INDEX
    Explanations

    phrases related to procedural steps or guidelines

    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
    174
    +0.13
    0.7%
    391
    +0.13
    0.7%
    103
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    175
    +0.13
    0.00
    121
    +0.13
    0.00
    21
    +0.12
    0.00
    Negative Logits
    documentclass
    -1.67
    fered
    -1.66
    lain
    -1.56
    ungen
    -1.53
    own
    -1.50
     MERCHANTABILITY
    -1.48
    robe
    -1.47
     night
    -1.46
    Room
    -1.45
    rums
    -1.44
    POSITIVE LOGITS
    \]]{}
    1.75
    ).](
    1.49
    \])]{}
    1.44
    oda
    1.39
    eto
    1.39
     ‘
    1.38
    onders
    1.36
     arise
    1.33
     sanctuary
    1.32
    ).)
    1.32
    Activations Density 0.000%

    No Known Activations