© 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. 2-RES-SM
    11. 31243
    Prev
    Next
    INDEX
    Explanations

    references to common medical conditions and their implications

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    326
    +0.20
    1.2%
    500
    +0.19
    1.1%
    414
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    500
    +0.20
    0.09
    326
    +0.19
    0.06
    118
    +0.12
    0.09
    Negative Logits
    attention
    -1.61
     patience
    -1.54
    }{|
    -1.53
     comments
    -1.49
    FORMATION
    -1.48
    };
    -1.45
    FLAGS
    -1.43
    ussions
    -1.41
     morale
    -1.41
    imize
    -1.40
    POSITIVE LOGITS
    ĥ½
    3.04
    <|outofrange|>
    2.91
    ↵↵
    2.91
    2.91
    ↵
    2.91
    ↵
    2.91
    2.91
    2.91
    2.91
    2.91
    Activations Density 0.628%

    No Known Activations