© 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. 10380
    Prev
    Next
    INDEX
    Explanations

    chemical elements or compounds

    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
    348
    +0.15
    0.8%
    78
    +0.13
    0.7%
    162
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    162
    +0.15
    0.01
    333
    +0.13
    0.02
    245
    +0.12
    0.01
    Negative Logits
    oddsidemargin
    -1.63
    esian
    -1.55
    hew
    -1.42
    ttes
    -1.41
     description
    -1.37
     homem
    -1.36
     shapes
    -1.33
    rology
    -1.32
     detail
    -1.31
     contractors
    -1.31
    POSITIVE LOGITS
    /âĪĴ
    2.47
    /+
    2.22
    mediated
    1.76
    glucose
    1.75
    ATP
    1.73
    ^,
    1.71
     cells
    1.70
    +^
    1.69
    cadherin
    1.66
    /-
    1.65
    Activations Density 0.082%

    No Known Activations