© 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. 14300
    Prev
    Next
    INDEX
    Explanations

    measurements related to food safety and preservation techniques

    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
    307
    +0.19
    1.2%
    271
    +0.18
    1.1%
    30
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.19
    0.06
    62
    +0.18
    0.04
    30
    +0.13
    0.03
    Negative Logits
     entity
    -1.51
     merged
    -1.47
    ↵
    -1.43
     itself
    -1.40
     });
    -1.40
     */,
    -1.39
     entities
    -1.38
     implicated
    -1.37
     omitted
    -1.36
     two
    -1.36
    POSITIVE LOGITS
    ĥ½
    4.63
    ¿
    4.46
    ¼
    4.25
    Ļª
    4.21
    ĺ
    4.15
    ´
    4.15
    Ī
    4.08
    İ
    4.07
    Ĵ
    4.05
    ½
    4.04
    Activations Density 0.840%

    No Known Activations