© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11885
    Prev
    Next
    INDEX
    Explanations

    punctuation marks used in the context of legal or formal documents

    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
    271
    +0.12
    0.8%
    353
    +0.11
    0.7%
    9
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    353
    +0.12
    0.01
    341
    +0.11
    0.01
    302
    +0.10
    0.01
    Negative Logits
     itself
    -1.71
     ($
    -1.58
     themselves
    -1.52
     towards
    -1.48
    olate
    -1.41
     mine
    -1.33
    ments
    -1.29
     anter
    -1.28
     ($\
    -1.25
     theirs
    -1.25
    POSITIVE LOGITS
    Ī
    3.23
    º
    3.21
    ¬
    3.11
    ¥
    3.10
    ¤
    3.08
    Ĩ
    2.98
    »
    2.91
    IJ
    2.90
    ¶
    2.88
    Ĭ
    2.88
    Activations Density 0.032%

    No Known Activations