© 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. 27567
    Prev
    Next
    INDEX
    Explanations

    truth statements about claims or assertions

    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
    478
    +0.14
    0.8%
    300
    +0.13
    0.7%
    314
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    300
    +0.14
    0.03
    495
    +0.13
    0.01
    443
    +0.12
    0.02
    Negative Logits
    ise
    -1.85
    ising
    -1.54
     under
    -1.46
    izes
    -1.45
    igation
    -1.42
    isation
    -1.42
    ize
    -1.40
    izing
    -1.37
     consultation
    -1.36
    ized
    -1.35
    POSITIVE LOGITS
    enz
    1.53
    ি
    1.48
    riad
    1.47
    enny
    1.46
    riors
    1.43
    celand
    1.43
    rior
    1.43
    rencies
    1.42
    ños
    1.42
    оваÑĤÑĮ
    1.35
    Activations Density 0.077%

    No Known Activations