© 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 EvalsExportsAPI 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. 13206
    Prev
    Next
    INDEX
    Explanations

    references to pagination and privacy-related terms

    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%
    9
    +0.13
    0.7%
    443
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    9
    +0.26
    0.05
    351
    +0.13
    0.06
    443
    +0.12
    0.04
    Negative Logits
    growth
    -1.54
     matter
    -1.52
    à°¿
    -1.42
    áĢ¯
    -1.32
     surrounding
    -1.32
     CONTRIBUTORS
    -1.31
    INCLUDING
    -1.30
    STE
    -1.29
    GREEK
    -1.29
    OPE
    -1.28
    POSITIVE LOGITS
    elines
    2.71
    Ŀ
    2.53
    ements
    2.53
    Ļ
    2.45
    etype
    2.42
    Ĺ
    2.39
    Ĩ
    2.37
    İ
    2.34
    etable
    2.33
    ¾
    2.33
    Activations Density 0.479%

    No Known Activations