© 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. 4-RES-SM
    11. 14030
    Prev
    Next
    INDEX
    Explanations

    references to copyright or ownership rights

    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
    21
    +0.19
    1.1%
    255
    +0.16
    0.9%
    78
    +0.14
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    333
    +0.19
    0.02
    7
    +0.16
    0.01
    265
    +0.14
    0.01
    Negative Logits
    ly
    -1.66
    abase
    -1.61
    ying
    -1.55
    ogue
    -1.50
    inois
    -1.50
    matically
    -1.48
    vironment
    -1.46
    nier
    -1.44
    imize
    -1.42
    inal
    -1.34
    POSITIVE LOGITS
     Reserved
    2.02
     reserved
    1.78
    ↵³³
    1.77
    ħ
    1.70
    ¬
    1.59
    ĥ
    1.56
    ²
    1.54
     granted
    1.53
    ©
    1.50
    à¸ĩ
    1.46
    Activations Density 0.064%

    No Known Activations