© 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. 2-RES-SM
    11. 31914
    Prev
    Next
    INDEX
    Explanations

    key terms related to transactions and timelines

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    178
    +0.17
    1.0%
    237
    +0.14
    0.8%
    40
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    178
    +0.17
    0.10
    237
    +0.14
    0.09
    501
    +0.10
    0.00
    Negative Logits
    «
    -3.67
    ³
    -3.40
    Ń
    -3.35
      ↵
    -3.32
    ↵
    -3.32
    -3.32
    <|outofrange|>
    -3.32
    -3.32
     ↵
    -3.32
    ↵
    -3.32
    POSITIVE LOGITS
    fall
    1.49
    itud
    1.47
    PING
    1.42
    birth
    1.39
    nal
    1.38
    VIS
    1.35
    JECT
    1.34
     accrued
    1.34
    vet
    1.34
    VERSION
    1.31
    Activations Density 2.311%

    No Known Activations