© 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. 28301
    Prev
    Next
    INDEX
    Explanations

    information related to political events and leaders

    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
    +0.19
    1.2%
    271
    +0.18
    1.1%
    23
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    324
    +0.19
    0.02
    420
    +0.18
    0.02
    90
    +0.15
    0.03
    Negative Logits
    itti
    -1.73
    sten
    -1.72
    izione
    -1.71
    ttes
    -1.68
    ieux
    -1.67
    entre
    -1.63
    thouse
    -1.61
    itas
    -1.58
    \]](
    -1.57
    itor
    -1.55
    POSITIVE LOGITS
    ĻĤ
    2.42
    ©
    2.15
    Īĺ
    1.98
    »
    1.96
    Į
    1.95
    Ī
    1.92
    Ŀ
    1.91
    ĺ
    1.91
    ½
    1.86
    ħ
    1.86
    Activations Density 0.165%

    No Known Activations