© 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. 10382
    Prev
    Next
    INDEX
    Explanations

    contrasting ideas and opposing viewpoints

    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
    25
    +0.20
    1.2%
    510
    +0.14
    0.8%
    156
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.20
    0.12
    25
    +0.14
    0.15
    58
    +0.13
    0.14
    Negative Logits
    ī
    -4.93
    <|outofrange|>
    -4.86
    -4.86
     ↵
    -4.86
    ↵
    -4.86
    ↵↵
    -4.86
    <|outofrange|>
    -4.86
    <|outofrange|>
    -4.86
    <|outofrange|>
    -4.86
    ↵
    -4.86
    POSITIVE LOGITS
    ly
    2.07
     thereof
    1.98
     ones
    1.96
     thereto
    1.90
    lies
    1.86
    ment
    1.85
    rians
    1.83
    heses
    1.73
     beams
    1.71
     ions
    1.71
    Activations Density 2.957%

    No Known Activations