© 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. 13456
    Prev
    Next
    INDEX
    Explanations

    references to statistical data and quantifiable results

    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
    397
    +0.17
    1.1%
    9
    +0.16
    1.1%
    29
    +0.15
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.17
    0.15
    9
    +0.16
    0.14
    352
    +0.15
    0.08
    Negative Logits
    $/
    -1.40
    rac
    -1.38
    while
    -1.24
    maker
    -1.24
     Monday
    -1.15
     [#
    -1.12
     Wednesday
    -1.11
    antine
    -1.08
     rage
    -1.08
     litter
    -1.08
    POSITIVE LOGITS
    ubicin
    1.34
    istration
    1.27
    ignon
    1.27
    achines
    1.25
    nai
    1.22
    isons
    1.20
    autres
    1.18
    EMENT
    1.18
    oltzmann
    1.15
     PURPOSE
    1.13
    Activations Density 4.194%

    No Known Activations