© 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. 26552
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and special characters

    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
    419
    +0.14
    0.8%
    374
    +0.13
    0.8%
    94
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    74
    +0.14
    0.03
    315
    +0.13
    0.02
    425
    +0.10
    0.03
    Negative Logits
    (_
    -1.71
    wards
    -1.70
    .).
    -1.68
    plasia
    -1.59
    condition
    -1.59
    cludes
    -1.54
    hab
    -1.51
    ($
    -1.48
    (['
    -1.47
    structor
    -1.43
    POSITIVE LOGITS
    ius
    1.47
    Ĭ
    1.43
     WARRANTIES
    1.40
     Appl
    1.39
    cki
    1.38
     Reynolds
    1.34
     Singh
    1.33
     nm
    1.33
     Pence
    1.33
    ³
    1.32
    Activations Density 0.113%

    No Known Activations