© 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. 13847
    Prev
    Next
    INDEX
    Explanations

    HTML attributes and tag 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
    397
    +0.17
    0.9%
    57
    +0.14
    0.8%
    349
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.17
    0.05
    57
    +0.14
    0.06
    78
    +0.12
    -0.01
    Negative Logits
     radiative
    -1.71
     filament
    -1.54
    rivolous
    -1.50
    endas
    -1.48
     Jessica
    -1.48
     feminism
    -1.44
     filaments
    -1.41
    ankton
    -1.40
    flix
    -1.39
    boat
    -1.37
    POSITIVE LOGITS
     Key
    3.66
     keys
    3.60
     Keys
    3.46
     key
    3.45
    key
    3.36
    Key
    3.24
    Keys
    3.15
    keys
    2.96
     KEY
    2.89
    KEY
    2.74
    Activations Density 0.823%

    No Known Activations