© 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. 9607
    Prev
    Next
    INDEX
    Explanations

    database operations and structures

    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
    269
    +0.21
    1.5%
    78
    +0.18
    1.3%
    232
    +0.12
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.21
    0.15
    78
    +0.18
    0.02
    9
    +0.12
    0.14
    Negative Logits
    lessly
    -1.46
    gers
    -1.45
    mable
    -1.34
    eral
    -1.34
    pile
    -1.33
    oler
    -1.30
    course
    -1.26
    rens
    -1.25
    arat
    -1.25
    ples
    -1.22
    POSITIVE LOGITS
    §
    2.81
    ©
    2.77
    Ķ
    2.75
    ľĵ
    2.69
    ®
    2.67
    Į
    2.67
    ĵ
    2.67
    Īĺ
    2.63
    ĻĤ
    2.60
    ĩ
    2.56
    Activations Density 2.815%

    No Known Activations