© 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. 24190
    Prev
    Next
    INDEX
    Explanations

    contexts related to specific circumstances or conditions

    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
    156
    +0.16
    0.9%
    205
    +0.12
    0.7%
    280
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.16
    0.13
    156
    +0.12
    0.08
    271
    +0.11
    0.04
    Negative Logits
     ↵
    -3.21
    ↵
    -3.21
    -3.21
    ↵Č
    -3.21
    ↵↵
    -3.21
    -3.21
    č↵
    -3.21
    <|outofrange|>
    -3.21
    ↵
    -3.21
    ↵
    -3.21
    POSITIVE LOGITS
    hell
    1.74
    urface
    1.69
    ide
    1.69
     asynchron
    1.67
     involving
    1.65
    afe
    1.62
    ETHOD
    1.62
    hoe
    1.61
    heet
    1.60
    ickness
    1.59
    Activations Density 0.573%

    No Known Activations