© 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. 13755
    Prev
    Next
    INDEX
    Explanations

    depository terms related to software licensing and redistribution

    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
    +0.14
    0.8%
    21
    +0.12
    0.7%
    234
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.14
    -0.01
    234
    +0.12
    0.01
    277
    +0.10
    0.01
    Negative Logits
    ses
    -2.11
    ards
    -1.94
    sen
    -1.83
    tar
    -1.79
    sed
    -1.74
    inals
    -1.70
    ries
    -1.69
    sel
    -1.69
    ton
    -1.66
    tin
    -1.65
    POSITIVE LOGITS
    Ń
    3.22
    ģ
    3.13
    ĩ
    2.92
    ¬
    2.91
    »
    2.88
    ¿
    2.85
    Ĩ
    2.83
    ¿½
    2.74
    ı
    2.71
    ŀ
    2.70
    Activations Density 0.193%

    No Known Activations