© 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. 13576
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial and economic challenges

    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
    306
    +0.25
    1.6%
    307
    +0.23
    1.5%
    21
    +0.17
    1.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.25
    0.15
    306
    +0.23
    0.07
    450
    +0.17
    0.01
    Negative Logits
    <|outofrange|>
    -5.57
    ↵↵
    -5.57
     ↵
    -5.57
     ↵
    -5.57
    -5.57
           ↵
    -5.57
    -5.57
    <|outofrange|>
    -5.57
    <|outofrange|>
    -5.57
    ↵↵↵
    -5.57
    POSITIVE LOGITS
    )\].
    1.77
    )\]
    1.57
    )}$,
    1.49
    )}$.
    1.44
    \]\].
    1.44
    )}}
    1.44
     BGCOLOR
    1.37
    000
    1.36
    )},\
    1.36
    )],
    1.35
    Activations Density 4.085%

    No Known Activations