© 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. 4-RES-SM
    11. 9590
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal disclaimers or license 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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    271
    +0.14
    0.8%
    157
    +0.12
    0.7%
    126
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    157
    +0.14
    0.01
    461
    +0.12
    0.01
    391
    +0.10
    0.01
    Negative Logits
    ↵
    -1.96
    -1.96
    -1.96
    <|outofrange|>
    -1.96
    -1.96
    ↵↵
    -1.96
    -1.96
    č↵č↵
    -1.96
    ↵↵
    -1.96
    -1.96
    POSITIVE LOGITS
    ÑĢаз
    1.89
    xsd
    1.70
    ом
    1.70
    лÑı
    1.68
    оÐ
    1.59
    Ñģли
    1.59
    ===========================
    1.57
    =====================
    1.57
    =================================
    1.56
    ==================================
    1.55
    Activations Density 0.028%

    No Known Activations