© 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 EvalsExportsinterp-engineNEWAPI 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. 29140
    Prev
    Next
    INDEX
    Explanations

    references to specific dates and events

    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
    156
    +0.20
    1.1%
    369
    +0.15
    0.8%
    60
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    307
    +0.20
    0.07
    477
    +0.15
    0.08
    203
    +0.12
    0.07
    Negative Logits
     anything
    -1.76
    >[
    -1.72
    '>
    -1.68
    :&
    -1.66
    pone
    -1.65
     %>
    -1.58
     deference
    -1.51
     >
    -1.50
     pity
    -1.50
     malice
    -1.49
    POSITIVE LOGITS
    ĨĴ
    2.55
    ħ
    2.41
    teenth
    2.27
    ĥ½
    2.23
    ¸
    2.23
    ģ
    2.21
    Ŀ
    2.19
    ¾
    2.15
    Ĵ
    2.14
    º
    2.11
    Activations Density 0.386%

    No Known Activations