© 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. 28734
    Prev
    Next
    INDEX
    Explanations

    symbols and notation related to mathematical expressions and equations

    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
    2
    +0.14
    0.8%
    350
    +0.12
    0.7%
    233
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.14
    0.05
    271
    +0.12
    0.02
    17
    +0.12
    0.03
    Negative Logits
    iline
    -1.67
     entire
    -1.59
     nowhere
    -1.43
    iginally
    -1.41
    ember
    -1.41
    uated
    -1.41
    aging
    -1.39
    onomous
    -1.38
    ]>
    -1.38
     realise
    -1.38
    POSITIVE LOGITS
    į
    1.75
    Ĵ
    1.65
    İ
    1.52
    Sports
    1.51
    ersion
    1.51
    §
    1.50
    ¾
    1.49
    ĥ½
    1.44
    ¬
    1.43
    ŀ
    1.43
    Activations Density 0.164%

    No Known Activations