© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11927
    Prev
    Next
    INDEX
    Explanations

    the verb "do" used in various contexts

    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
    78
    +0.15
    0.9%
    49
    +0.12
    0.7%
    245
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    295
    +0.15
    0.03
    349
    +0.12
    0.03
    49
    +0.11
    0.04
    Negative Logits
    izing
    -1.95
    ly
    -1.82
    ized
    -1.72
    itive
    -1.61
    ual
    -1.59
    izer
    -1.59
    ulent
    -1.52
    night
    -1.50
    TRODUCTION
    -1.49
     ways
    -1.49
    POSITIVE LOGITS
    xygen
    2.73
    ®
    2.43
    ctrine
    2.31
    herty
    2.23
    ctype
    2.13
    ħ
    2.08
    ppler
    2.05
    ozy
    1.98
    vet
    1.95
    İ
    1.90
    Activations Density 0.130%

    No Known Activations