© 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. 2-RES-SM
    11. 31494
    Prev
    Next
    INDEX
    Explanations

    structured or formatted content, particularly in markup languages

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    111
    +0.18
    1.0%
    479
    +0.14
    0.8%
    209
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    456
    +0.18
    0.02
    74
    +0.14
    0.01
    209
    +0.13
    0.02
    Negative Logits
    []{
    -1.56
    ?).
    -1.53
    .[]{
    -1.51
    ?’
    -1.47
     intended
    -1.46
    à¯ģ
    -1.43
    selling
    -1.41
    prototype
    -1.37
     []{
    -1.35
     shots
    -1.35
    POSITIVE LOGITS
     view
    1.64
    ·¸
    1.64
    ³
    1.47
    ://
    1.47
    ild
    1.47
    uture
    1.41
    orld
    1.40
     gently
    1.40
    ucle
    1.38
    atinib
    1.38
    Activations Density 0.084%

    No Known Activations