© 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. 14750
    Prev
    Next
    INDEX
    Explanations

    information concerning legal agreements, particularly in the context of partnership and asset distribution

    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
    348
    +0.27
    1.7%
    78
    +0.14
    0.8%
    378
    +0.10
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.27
    0.08
    348
    +0.14
    0.04
    78
    +0.10
    -0.05
    Negative Logits
    -5.73
    -5.73
    -5.73
     ↵
    -5.73
    <|outofrange|>
    -5.73
    ↵
    -5.73
    <|outofrange|>
    -5.73
    -5.73
    -5.73
    ↵↵
    -5.73
    POSITIVE LOGITS
     respectively
    2.78
    .).
    2.23
    ].
    2.12
     alike
    2.07
    .](
    2.07
    ]."
    2.01
    }.$
    1.99
    .);
    1.97
    ]{}.
    1.96
    .'"
    1.92
    Activations Density 2.163%

    No Known Activations