© 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. 2-RES-SM
    11. 13277
    Prev
    Next
    INDEX
    Explanations

    terms related to various types of sheets and dough in cooking 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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    156
    +0.19
    1.1%
    144
    +0.13
    0.8%
    26
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    172
    +0.19
    0.02
    144
    +0.13
    0.01
    504
    +0.12
    0.01
    Negative Logits
     spite
    -1.66
     luck
    -1.64
     rainy
    -1.64
     wonder
    -1.59
     realize
    -1.55
     realise
    -1.53
     grin
    -1.52
     flaw
    -1.50
     happen
    -1.48
     sudden
    -1.47
    POSITIVE LOGITS
    ĻĤ
    1.99
    Ģ
    1.99
    rock
    1.83
    au
    1.68
    lections
    1.67
    ahead
    1.63
    ģ
    1.63
    top
    1.63
    sted
    1.63
    metal
    1.60
    Activations Density 0.146%

    No Known Activations