© 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. 25231
    Prev
    Next
    INDEX
    Explanations

    phrases indicating permissions or terms of service

    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
    400
    +0.12
    0.7%
    290
    +0.11
    0.6%
    495
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    249
    +0.12
    0.03
    76
    +0.11
    0.03
    501
    +0.11
    0.02
    Negative Logits
    Ŀ
    -4.19
    ĭ
    -3.94
    ±
    -3.90
    ¦
    -3.69
    ©
    -3.65
    ŀ
    -3.64
    Ħ
    -3.62
    ¨
    -3.58
    ª
    -3.55
    Ĥ¬
    -3.51
    POSITIVE LOGITS
     LIABILITY
    1.70
     unrestricted
    1.67
     restrictions
    1.67
     invariance
    1.66
     immunity
    1.65
     parameters
    1.65
     protections
    1.65
     unlimited
    1.63
     expire
    1.62
     procedural
    1.61
    Activations Density 0.420%

    No Known Activations