© 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. 31538
    Prev
    Next
    INDEX
    Explanations

    references to governmental or administrative functions and activities

    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
    136
    +0.15
    0.9%
    23
    +0.15
    0.9%
    271
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.15
    0.10
    136
    +0.15
    -0.01
    203
    +0.14
    0.07
    Negative Logits
    ±
    -3.89
    ļ
    -3.87
    »¿
    -3.87
    ¢
    -3.81
    Ń
    -3.79
    ĻĤ
    -3.74
    ĩ
    -3.72
    Ģ
    -3.69
    ĥ½
    -3.66
    ¿½
    -3.65
    POSITIVE LOGITS
    omitempty
    1.91
    etc
    1.83
     etc
    1.70
    ...,
    1.46
    fav
    1.45
    ingen
    1.42
    should
    1.38
     courtesy
    1.35
     edge
    1.35
     ...)
    1.34
    Activations Density 0.848%

    No Known Activations