© 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. 28530
    Prev
    Next
    INDEX
    Explanations

    past tense forms 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
    439
    +0.14
    0.8%
    195
    +0.11
    0.6%
    423
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    195
    +0.14
    0.08
    485
    +0.11
    0.06
    348
    +0.11
    0.09
    Negative Logits
    »¿
    -1.78
    ľĵ
    -1.75
    holders
    -1.57
    bed
    -1.54
    angled
    -1.53
    oused
    -1.49
    anged
    -1.46
    £
    -1.45
    ed
    -1.44
    utton
    -1.44
    POSITIVE LOGITS
    rika
    1.55
    ges
    1.52
     ///
    1.44
    rien
    1.41
    opf
    1.40
    ocs
    1.38
    rol
    1.38
    nai
    1.35
    rine
    1.35
    wort
    1.35
    Activations Density 0.975%

    No Known Activations