© 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 EvalsExportsAPI 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. 28115
    Prev
    Next
    INDEX
    Explanations

    phrases involving the infinitive form of verbs

    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
    186
    +0.17
    1.0%
    69
    +0.16
    1.0%
    142
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.17
    0.14
    411
    +0.16
    0.10
    151
    +0.12
    0.08
    Negative Logits
    ishly
    -1.66
     alone
    -1.60
    icious
    -1.54
    rically
    -1.49
    ãĤį
    -1.47
    uit
    -1.47
     asleep
    -1.45
    arily
    -1.42
     together
    -1.39
    ously
    -1.38
    POSITIVE LOGITS
    ms
    1.66
     be
    1.61
    hang
    1.53
     DOI
    1.51
     reproduce
    1.49
    fu
    1.48
    fac
    1.48
    ppings
    1.47
    pless
    1.46
    ¹
    1.43
    Activations Density 1.319%

    No Known Activations