© 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. 24798
    Prev
    Next
    INDEX
    Explanations

    words related to the embedding and completion of content

    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
    289
    +0.16
    0.9%
    356
    +0.12
    0.7%
    3
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.16
    0.02
    380
    +0.12
    0.03
    348
    +0.11
    0.03
    Negative Logits
    ://
    -1.51
    (@"
    -1.47
    cgi
    -1.39
     derivative
    -1.35
     "/
    -1.34
     github
    -1.32
    ASSERT
    -1.31
    INC
    -1.30
    rb
    -1.30
     better
    -1.29
    POSITIVE LOGITS
    urity
    1.74
    ène
    1.65
    lings
    1.65
    uity
    1.61
    ility
    1.58
     anaest
    1.54
    oring
    1.52
    uates
    1.49
    uture
    1.48
    ling
    1.47
    Activations Density 0.223%

    No Known Activations