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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 28535
    Prev
    Next
    INDEX
    Explanations

    scientific terms and variables related to physics and engineering concepts

    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
    369
    +0.17
    1.0%
    2
    +0.16
    0.9%
    156
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    369
    +0.17
    0.01
    350
    +0.16
    0.03
    421
    +0.12
    0.01
    Negative Logits
    lining
    -2.13
    doing
    -1.80
    batim
    -1.77
    book
    -1.63
    =============
    -1.57
    lando
    -1.54
    come
    -1.53
    efore
    -1.53
    boarding
    -1.46
    land
    -1.45
    POSITIVE LOGITS
    zzle
    2.06
     rays
    1.79
    imeter
    1.68
    ña
    1.62
    pper
    1.59
    ñ
    1.59
    ī
    1.53
     belt
    1.51
    isance
    1.48
    §
    1.44
    Activations Density 0.197%

    No Known Activations