© 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 EvalsExportsAPI 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. 26455
    Prev
    Next
    INDEX
    Explanations

    references to political figures and events related to investigations and controversies

    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
    279
    +0.12
    0.7%
    98
    +0.12
    0.7%
    20
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.12
    0.18
    34
    +0.12
    0.15
    362
    +0.11
    0.12
    Negative Logits
    Ļª
    -2.25
    ĥ½
    -2.23
    ĻĤ
    -2.22
    ¨
    -2.19
    ¼
    -2.08
    IJ
    -2.07
    Ĵ
    -2.05
     therefrom
    -2.04
     thereto
    -1.95
    Ĭ
    -1.94
    POSITIVE LOGITS
     forum
    1.98
    NBC
    1.81
    igan
    1.79
    http
    1.75
    xon
    1.75
    https
    1.75
     panel
    1.65
    ]:
    1.63
     Biden
    1.61
    umbo
    1.60
    Activations Density 3.176%

    No Known Activations