© 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. 14551
    Prev
    Next
    INDEX
    Explanations

    legal terms and references to court cases

    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
    21
    +0.26
    1.5%
    342
    +0.12
    0.7%
    279
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    369
    +0.26
    0.04
    415
    +0.12
    0.04
    342
    +0.11
    0.03
    Negative Logits
    ¼
    -2.49
    º
    -2.28
    »¿
    -2.27
    Īĺ
    -2.13
    ª
    -2.11
    ¤
    -2.03
    ¿
    -2.03
    ¹
    -2.01
    ¸
    -1.99
    ±
    -1.96
    POSITIVE LOGITS
    .,
    2.46
    .);
    2.25
    .;
    2.16
    .:
    2.03
    .),
    1.96
    .--
    1.79
    .*,
    1.75
    .).
    1.72
    .—
    1.61
    ).)
    1.56
    Activations Density 0.237%

    No Known Activations