© 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. 26530
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers and alphanumeric 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
    240
    +0.13
    0.8%
    243
    +0.13
    0.7%
    127
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    335
    +0.13
    0.15
    243
    +0.13
    0.17
    239
    +0.12
    0.16
    Negative Logits
    ĻĤ
    -3.21
    Īĺ
    -2.97
    ¹
    -2.65
    Ŀ
    -2.63
    ŀ
    -2.61
    ¦
    -2.56
    °
    -2.56
    ħ
    -2.49
    ĺ
    -2.48
    ĵ
    -2.42
    POSITIVE LOGITS
     numbered
    1.68
     thereof
    1.48
     Of
    1.44
    Of
    1.42
     of
    1.41
    uge
    1.37
    ificantly
    1.36
    opot
    1.32
    mentioned
    1.31
     owing
    1.30
    Activations Density 3.695%

    No Known Activations