© 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. 14969
    Prev
    Next
    INDEX
    Explanations

    genetic markers and mutations related to the TP53 gene and immunoglobulin G (IgG) levels

    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
    98
    +0.12
    0.7%
    412
    +0.11
    0.6%
    73
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    412
    +0.12
    0.03
    11
    +0.11
    0.02
    98
    +0.11
    0.01
    Negative Logits
     trouble
    -1.65
    comes
    -1.62
     enough
    -1.59
     Defender
    -1.58
     certainty
    -1.53
    arers
    -1.47
     sure
    -1.45
     accurate
    -1.42
    dere
    -1.41
     fact
    -1.40
    POSITIVE LOGITS
    £
    2.67
    İ
    2.62
    ĵ
    2.62
    ĩ
    2.50
    ı
    2.39
    Ĭ
    2.39
    ª
    2.35
    ģ
    2.32
    APDH
    2.29
    Ī
    2.23
    Activations Density 0.047%

    No Known Activations