© 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. 4-RES-SM
    11. 14947
    Prev
    Next
    INDEX
    Explanations

    references to bibliographic or publishing 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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    89
    +0.13
    0.7%
    156
    +0.12
    0.7%
    385
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    359
    +0.13
    0.12
    89
    +0.12
    0.03
    398
    +0.11
    -0.01
    Negative Logits
    illance
    -1.80
     ecosystem
    -1.80
     IoT
    -1.72
    opause
    -1.68
    reprene
    -1.68
     Uber
    -1.63
     killing
    -1.63
    à±ģ
    -1.59
    cosystem
    -1.58
     adren
    -1.56
    POSITIVE LOGITS
     manuscripts
    3.81
     manuscript
    3.53
     copies
    3.45
    uscript
    3.38
     editions
    3.36
     reprinted
    3.05
     printed
    3.02
     copy
    2.98
     illustrations
    2.91
     citations
    2.90
    Activations Density 3.277%

    No Known Activations