© 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. 25589
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific letters or characters in a text

    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
    478
    +0.21
    1.2%
    23
    +0.19
    1.1%
    410
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.21
    0.02
    395
    +0.19
    0.01
    501
    +0.15
    0.01
    Negative Logits
    naire
    -1.88
     Ltd
    -1.73
     peroxidase
    -1.73
     whereby
    -1.72
    alities
    -1.70
    amiento
    -1.70
    ÅĽci
    -1.65
    agem
    -1.64
    ally
    -1.64
    ional
    -1.59
    POSITIVE LOGITS
    ĥ
    4.02
    Ľ
    3.88
    ĸ´
    3.85
    Īĺ
    3.83
    ²
    3.78
    Ĩ
    3.75
    ³
    3.73
    Ĵ
    3.71
    Ĥ¬
    3.64
    ¥
    3.62
    Activations Density 0.072%

    No Known Activations