© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 4-RES-SM
    6. 11668
    Prev
    Next
    INDEX
    Explanations

    specific punctuation marks and formatting characters in a document

    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
    +0.17
    1.0%
    88
    +0.14
    0.8%
    182
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    295
    +0.17
    0.07
    88
    +0.14
    0.05
    365
    +0.13
    0.06
    Negative Logits
     perpendicular
    -1.65
     measuring
    -1.54
    otyped
    -1.51
     contempor
    -1.47
     opposite
    -1.46
    ulating
    -1.44
    gie
    -1.41
     antic
    -1.40
     synonymous
    -1.40
    uating
    -1.39
    POSITIVE LOGITS
    ©
    3.93
    ½
    3.61
    ¼
    3.58
    Ĺ
    3.57
    ±
    3.52
    ª
    3.49
    Ķ
    3.49
    ¤
    3.47
    ¿
    3.43
    Ĩ
    3.39
    Activations Density 0.331%

    No Known Activations