© 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. 13003
    Prev
    Next
    INDEX
    Explanations

    action verbs indicating achievement or significant 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/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
    510
    +0.14
    0.8%
    282
    +0.12
    0.7%
    217
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    472
    +0.14
    0.08
    282
    +0.12
    0.07
    287
    +0.12
    0.09
    Negative Logits
    §
    -5.08
    Ĩ
    -4.95
    İ
    -4.95
    IJ
    -4.94
    Īĺ
    -4.84
    ĭ
    -4.81
    ī
    -4.72
    ħ
    -4.71
    Ļª
    -4.70
    ĩ
    -4.69
    POSITIVE LOGITS
     cakes
    1.53
    ivat
    1.49
    elic
    1.48
     nor
    1.46
    ele
    1.46
     methamphetamine
    1.44
     contrary
    1.41
    gage
    1.40
    cyst
    1.39
    oline
    1.39
    Activations Density 0.688%

    No Known Activations