© 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 EvalsExportsAPI 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. 27598
    Prev
    Next
    INDEX
    Explanations

    technical terms and syntax related to programming or data structures

    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
    156
    +0.33
    1.9%
    136
    +0.14
    0.8%
    17
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.33
    0.04
    136
    +0.14
    0.00
    271
    +0.12
    0.00
    Negative Logits
    ppat
    -1.44
    jax
    -1.37
    assis
    -1.28
     Auto
    -1.25
     Redistributions
    -1.25
     heels
    -1.24
    home
    -1.23
    омÑĥ
    -1.22
     Suite
    -1.19
    erty
    -1.18
    POSITIVE LOGITS
     probable
    1.48
    dered
    1.47
    ½
    1.46
    verte
    1.44
    ?",
    1.38
     neuron
    1.37
    semin
    1.35
    Ħ
    1.32
    igm
    1.32
    pret
    1.31
    Activations Density 0.468%

    No Known Activations