© 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. 12570
    Prev
    Next
    INDEX
    Explanations

    terms related to printing processes and output formats

    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
    490
    +0.20
    1.1%
    156
    +0.18
    1.0%
    354
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    490
    +0.20
    0.03
    215
    +0.18
    0.03
    148
    +0.12
    0.00
    Negative Logits
    ¼
    -2.90
    ·
    -2.81
    ĭ
    -2.80
    ½
    -2.76
    Į
    -2.66
    º
    -2.55
    IJ
    -2.48
    Ĭ
    -2.46
    ·¸
    -2.41
    ĥ
    -2.41
    POSITIVE LOGITS
    ings
    2.04
    heads
    1.97
    INGS
    1.89
    outs
    1.88
     newspapers
    1.71
    head
    1.69
     paper
    1.67
    able
    1.66
    ables
    1.65
     money
    1.64
    Activations Density 0.143%

    No Known Activations