© 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. 14534
    Prev
    Next
    INDEX
    Explanations

    references to amino acids and their interactions within biochemical reactions

    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
    +0.21
    1.2%
    288
    +0.13
    0.7%
    448
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    448
    +0.21
    0.02
    203
    +0.13
    0.01
    288
    +0.13
    0.01
    Negative Logits
    iring
    -1.58
    htra
    -1.51
    ufact
    -1.50
    oscope
    -1.46
    usiness
    -1.43
     retiring
    -1.38
    iplex
    -1.37
    prises
    -1.36
    rology
    -1.35
     Caption
    -1.34
    POSITIVE LOGITS
    Ĩ
    2.68
    Ĥ
    2.60
    ¼
    2.50
    Ľ
    2.43
    §
    2.42
    ł
    2.40
    ĵ
    2.40
    Ħ
    2.39
    ¿
    2.35
    Ĵ
    2.34
    Activations Density 0.026%

    No Known Activations