© 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. 10451
    Prev
    Next
    INDEX
    Explanations

    dates

    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
    375
    +0.11
    0.6%
    21
    +0.11
    0.6%
    281
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    336
    +0.11
    0.03
    375
    +0.11
    0.02
    448
    +0.11
    0.03
    Negative Logits
    emic
    -1.69
     grasp
    -1.66
     probability
    -1.66
    eted
    -1.51
    eting
    -1.46
    ]{
    -1.42
     likelihood
    -1.42
    etter
    -1.39
    ictionary
    -1.38
    eries
    -1.36
    POSITIVE LOGITS
    itime
    2.43
    ©
    2.29
    vell
    2.17
    quette
    2.13
    ĻĤ
    2.12
    «
    2.01
    ¬
    2.00
    ĭ
    1.90
    riages
    1.90
    ibel
    1.90
    Activations Density 0.073%

    No Known Activations