© 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. 26550
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "in" and its contextual relevance

    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
    186
    +0.13
    0.8%
    400
    +0.13
    0.7%
    407
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    282
    +0.13
    0.10
    407
    +0.13
    0.10
    69
    +0.13
    0.11
    Negative Logits
     concludes
    -1.58
     below
    -1.34
     proceeds
    -1.34
    ings
    -1.33
     RNAs
    -1.33
     certificates
    -1.32
    !
    -1.31
     Honorable
    -1.29
     ends
    -1.28
     crews
    -1.28
    POSITIVE LOGITS
    ĻĤ
    2.77
    ĥ½
    2.65
    ļ
    2.53
    ľĵ
    2.52
              ↵
    2.52
    2.52
    ↵
    2.52
    ↵
    2.52
    ↵  âĢĥ
    2.52
    ↵            ↵
    2.52
    Activations Density 1.123%

    No Known Activations