© 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. 1-RES-SM
    11. 28743
    Prev
    Next
    INDEX
    Explanations

    references to time periods and durations

    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
    235
    +0.12
    0.7%
    459
    +0.12
    0.7%
    5
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    374
    +0.12
    0.06
    459
    +0.12
    0.06
    235
    +0.11
    0.05
    Negative Logits
     thereof
    -1.64
    ĥ
    -1.61
    )$-
    -1.48
    »¿
    -1.48
    amycin
    -1.46
     placebo
    -1.45
    edu
    -1.45
     domains
    -1.44
    ·¸
    -1.42
     possible
    -1.39
    POSITIVE LOGITS
    "));
    1.63
    coming
    1.55
    forth
    1.52
    ovsk
    1.47
     Professor
    1.43
    nai
    1.43
    avia
    1.42
    mares
    1.41
    brate
    1.39
     however
    1.38
    Activations Density 0.331%

    No Known Activations