© 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. 29191
    Prev
    Next
    INDEX
    Explanations

    HTML or XML tags and attributes in a document

    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
    346
    +0.14
    0.8%
    227
    +0.12
    0.7%
    329
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    329
    +0.14
    0.04
    53
    +0.12
    0.04
    116
    +0.12
    0.03
    Negative Logits
    ordo
    -1.59
     likes
    -1.55
    atz
    -1.55
     regimes
    -1.54
     regime
    -1.42
     Rptr
    -1.41
    dom
    -1.41
     unit
    -1.40
    \.
    -1.40
    kernel
    -1.38
    POSITIVE LOGITS
    »
    3.42
    ķ
    3.13
    ª
    3.13
    »¿
    3.13
    ¢
    3.07
    ĨĴ
    3.04
    ¿½
    3.03
    Īĺ
    2.78
    Ĺ
    2.73
    ¥
    2.72
    Activations Density 0.347%

    No Known Activations