© 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. 4-RES-SM
    11. 12431
    Prev
    Next
    INDEX
    Explanations

    references to brands and branding concepts

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    127
    +0.13
    0.7%
    62
    +0.12
    0.7%
    193
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    193
    +0.13
    0.03
    127
    +0.12
    0.03
    38
    +0.12
    0.03
    Negative Logits
    £
    -2.64
    Ŀ
    -2.51
    Ĥ
    -2.42
    IJ
    -2.40
    ļ
    -2.32
    ĺ
    -2.29
    ¦
    -2.25
    ¥
    -2.09
    ±
    -2.03
    º
    -2.01
    POSITIVE LOGITS
    ishing
    2.80
     new
    2.31
    ished
    2.13
    new
    2.04
    iest
    1.94
    ishment
    1.93
    ishes
    1.89
     loyalty
    1.84
    olini
    1.79
     ambassador
    1.78
    Activations Density 0.380%

    No Known Activations