© 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. 4-RES-SM
    11. 11355
    Prev
    Next
    INDEX
    Explanations

    numerical data points and sequences

    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
    150
    +0.23
    1.5%
    89
    +0.20
    1.4%
    337
    +0.20
    1.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    78
    +0.23
    0.01
    89
    +0.20
    0.07
    150
    +0.20
    0.09
    Negative Logits
    htra
    -1.27
    ogn
    -1.18
    edin
    -1.15
    inai
    -1.14
    npmjs
    -1.13
    ions
    -1.13
    etimes
    -1.12
    izations
    -1.10
    phia
    -1.10
     orders
    -1.10
    POSITIVE LOGITS
     stars
    1.55
    lightenment
    1.21
     ages
    1.19
     pupils
    1.17
     prism
    1.16
    kers
    1.15
     star
    1.10
    (:
    1.09
    sheet
    1.08
    upal
    1.08
    Activations Density 1.798%

    No Known Activations