© 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. 1-RES-SM
    11. 26001
    Prev
    Next
    INDEX
    Explanations

    terms related to definitions or established concepts

    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
    376
    +0.15
    0.9%
    470
    +0.15
    0.8%
    380
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    470
    +0.15
    0.02
    380
    +0.15
    0.02
    367
    +0.13
    0.02
    Negative Logits
    worth
    -2.13
    obe
    -1.78
    ricular
    -1.64
    lotte
    -1.64
    bery
    -1.58
    lev
    -1.57
    wood
    -1.52
    burn
    -1.50
    oca
    -1.42
     dass
    -1.41
    POSITIVE LOGITS
    ĻĤ
    2.05
     Parenthood
    2.05
    ément
    1.81
     between
    1.56
    ally
    1.55
    GMP
    1.55
    inally
    1.53
    ĺ
    1.48
    utively
    1.47
     upstream
    1.46
    Activations Density 0.050%

    No Known Activations