© 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. 25907
    Prev
    Next
    INDEX
    Explanations

    words indicating probability or likelihood

    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
    23
    +0.15
    0.9%
    435
    +0.12
    0.7%
    59
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    435
    +0.15
    0.03
    236
    +0.12
    0.03
    327
    +0.11
    0.03
    Negative Logits
    ĭ
    -2.80
    ©
    -2.76
    ĵ
    -2.62
    Ĩ
    -2.53
    ½
    -2.51
    Ĭ
    -2.46
    Ĵ
    -2.46
    ĥ½
    -2.43
    Į
    -2.41
    ī
    -2.38
    POSITIVE LOGITS
     encounter
    1.64
     undetect
    1.64
     breathing
    1.63
     unconscious
    1.63
    gaard
    1.50
    weather
    1.49
     glimpse
    1.47
     hurt
    1.46
     prey
    1.41
    fire
    1.40
    Activations Density 0.115%

    No Known Activations