© 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. 1-RES-SM
    11. 25288
    Prev
    Next
    INDEX
    Explanations

    xml namespace declarations

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    306
    +0.15
    0.8%
    71
    +0.14
    0.8%
    448
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.15
    0.01
    448
    +0.14
    0.01
    252
    +0.11
    0.01
    Negative Logits
    ship
    -1.45
    ons
    -1.41
    rise
    -1.37
    oxide
    -1.32
    oned
    -1.32
    frastructure
    -1.31
    stant
    -1.31
    liest
    -1.30
    destruct
    -1.30
     chance
    -1.30
    POSITIVE LOGITS
    ERTY
    1.85
    IFIC
    1.59
     WARRANTY
    1.45
    idity
    1.39
    ynman
    1.38
    urname
    1.36
     Names
    1.35
    ÑĮ
    1.32
     vars
    1.31
    rophys
    1.30
    Activations Density 0.077%

    No Known Activations