© 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. 10241
    Prev
    Next
    INDEX
    Explanations

    references to licenses associated with Apache software

    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
    21
    +0.18
    1.1%
    20
    +0.12
    0.7%
    27
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    460
    +0.18
    0.01
    27
    +0.12
    0.02
    334
    +0.11
    0.02
    Negative Logits
    ary
    -1.60
    aries
    -1.57
    etable
    -1.43
    ETS
    -1.34
    ulate
    -1.32
    ages
    -1.31
    ionage
    -1.30
    bersome
    -1.29
    ionate
    -1.27
     Agg
    -1.27
    POSITIVE LOGITS
    âĢ¦]
    1.59
    glich
    1.56
    esty
    1.36
    .]
    1.32
    =/
    1.30
    àª
    1.29
    ãĤģ
    1.28
    ап
    1.26
    à²
    1.26
    à³
    1.25
    Activations Density 0.147%

    No Known Activations