© 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. 11343
    Prev
    Next
    INDEX
    Explanations

    specific references to the intestines or conditions related to them

    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
    85
    +0.12
    0.6%
    10
    +0.11
    0.6%
    250
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    85
    +0.12
    0.02
    506
    +0.11
    0.01
    386
    +0.11
    0.01
    Negative Logits
    ILY
    -1.84
     themselves
    -1.78
    place
    -1.64
     sense
    -1.62
     application
    -1.54
     itself
    -1.50
     footing
    -1.36
     BASIS
    -1.35
    ymoon
    -1.35
     applications
    -1.33
    POSITIVE LOGITS
    ĥ½
    2.73
    İ
    2.49
    Į
    2.47
    £
    2.46
    ¦
    2.43
    ¡
    2.41
    Ĭ
    2.37
    ³
    2.37
    uitively
    2.35
    Ĵ
    2.17
    Activations Density 0.083%

    No Known Activations